Good Papers

Showing Mechanistic interpretability Show all papers

80%Must read
?Must readVote to see the score
arXivMechanistic interpretability

Lingtai: What Concept Geometry Reveals—and Does Not Reveal—About LLM Inference

Lingtai introduces a training-free concept telemetry layer that reveals inference-time uncertainty-linked activity and execution-specific trajectory structures in LLMs without tracking correctness.

Jiangang Chen

Published Oct 1, 2026 · 0 citations

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 3/5
medium 7/10
strict 2/5
80%Must read
?Must readVote to see the score
arXivNew York University ShanghaiMechanistic interpretability

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

We introduce CIA to measure chain-of-thought alignment with internal reasoning, finding low alignment that post-training improves substantially while maintaining accuracy.

Yihuai Hong, Shauli Ravfogel, Chen Zhao, Eunsol Choi

Published Sep 30, 2026 · 0 citations · ▲ 2 on Hugging Face · Code ★ 1

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Shanghai Jiao TongThe Chinese University of Hong KHarbin Institute of TechnologyShanghai Artificial IntelligenceTsinghuaMechanistic interpretability

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs

Shaobo Wang, Yongliang Miao, YuanCheng Liu, Qianli Ma and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026YorkFAR.AIGoodfire AIMechanistic interpretability

Cross-Model Circuit Discovery

Harrish Thasarathan, Matthew Kowal, Thomas Fel, Kosta Derpanis

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Carnegie MellonMechanistic interpretability

Concept-Localized Generative Representations

Amanda Merkley

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026UW MadisonU Wisconsin-MadisonU Wisconsin - MadisonMechanistic interpretability

Spectral-Spatial Interpretation

Haotian Ma, Ruqi Yang, Philip Townsend

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026OralUniversiteit GentHebrewU & UCLGoogle DeepMindAnthropicMechanistic interpretability

LoRAcles: Self-Supervised Weight-Space Interpretability at Scale

Celeste De Schamphelaere, Jan Bauer, Neel Nanda, Euan Ong

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Harbin Institute of TechnologyMechanistic interpretability

How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location

Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu and 1 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026SimplexU ManchesterSimplex, Astera InstituteMechanistic interpretability

What Arranges Features in Activation Space? Non-Classical Predictive Geometry in Next-Token Predictors

Adam Shai, Thomas J Elliott, Paul Riechers

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Case Western ReserveMechanistic interpretability

Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations

Bryce Grant, Peng Wang

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026KAISTKorea Advanced Institute of ScieMechanistic interpretability

Attention Sinks as Spectral Spikes: A Mechanism Analysis of Gated Attention

Seojin Kim, Yehjin Shin, Noseong Park

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 0/5
medium 1/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026YaleEberhard-Karls-Universität TübinIEHarvardMechanistic interpretability

Reading Positional Coupling in Transformers with Diffusion Scores

Savik Kinger, Johannes Bertram, Luciano Dyballa, Andy Keller and 1 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026OralU OxfordMeta / University of OxfordOxfordMechanistic interpretability

The Sign Code: The Hidden Binary Nature of Deep Networks

Niclas A Göring, Shuofeng Zhang, Roi Holtzman, yoonsoo nam and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Korea Advanced Institute of ScieKAISTMechanistic interpretability

Decision Path Tracing for Causal Analysis in Transformers

Won Jo, Dahee Kwon, Jongeun Baek, Cheongwoong Kang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Dartmouth CollegeMechanistic interpretability

Knowing Without Saying: How Contextual Evidence Survives but Fails to Surface in Transformers

Ruochen Jin, Tianyu Pang, Chenxi Lin, Lei Hsiung and 4 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026TechnionNVIDIA / TechnionComputer Science Department, TecMechanistic interpretability

Learnable Spectral Activations

Tamir Shor, Or Litany, Alex M Bronstein

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026HanyangHanyang UniverstyMechanistic interpretability

Right Results, Wrong Reasons: Auditing Behavioral Reliance in Motion Forecasting

Geonyeong Park, Byounghun Park, Nayoung Kim, Kyungmin Kim and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U CambridgeMechanistic interpretability

How Language Models Compress and Compare: Understanding Selection with Token Covariance Maps

Moshe Eliasof

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Institute of Information EngineeShanghai University of Finance aCMUIQuest ResearchRenmin University of ChinaMechanistic interpretability

Iterative Nonlinear Computation Underlying Abstract Reasoning

Zitian Gao, Yilong Chen, Yihao Xiao, Xinyu Yang and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026National University of SingaporeChinese University of Hong KongThe Hong Kong University of ScieMechanistic interpretability

Concept-Based Mechanistic Interpretability Needs a Concrete Evaluation Paradigm

Yiming Tang, Qinglin Qi, LIN Zheng, Dianbo Liu

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Amsterdam / National TaiwanU AmsterdamMassachusetts Institute of TechnMechanistic interpretability

JEPAWG: Interpretable Hypernetworks for Weight-Space Physics

Tobias Göbel, Julian R Ebelt, Zier Mensch, Mathis Gerdes and 1 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026OralU British ColumbiaGuangdong Polytechnic NormalGriffithShenzhen Institutes of Advanced Mechanistic interpretability

IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition

Chaojie Ji, Jian Xu, He Zhang, Hongyan Wu and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NortheasternUniversite de MontrealMechanistic interpretability

What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation

Tinghe Zhang, Yucheng Xiao, Alex Lamb

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Tsinghua, Chinese Academy of SciencesMechanistic interpretability

From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers

Shurui Zheng, Fanhong Li, Zhixing Huang, Zixi Li and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The University of SydneyU SydneyU Sydney, University of SydneyHong Kong University of Science DeepWisdomMechanistic interpretability

ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection

Qingwen Zeng, Zehao Fu, Shuyu Meng, Linghan Huang and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Universitat Autònoma de BarcelonU Exeter"Computer Vision Center, BaIndian Statistical InstituteU SurreyMechanistic interpretability

Can Circuit Alignment Predict OOD Generalization?

Ayan Banerjee, ABHRA CHAUDHURI, Josep Llados, Umapada Pal and 1 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026UESTCFudanPontifícia Universidade CatólicaIndian Institute of Technology IMechanistic interpretability

Where Reusable Computation Becomes Detectable: Solution-Frame Path Triage for Modular-Arithmetic Grokking

Ruian Lei, Ruoxi Jiang, Marley M Vellasco, M. Tanveer and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U AlbertaCaltechMechanistic interpretability

Mechanistic Interpretability with Sparse Autoencoder Neural Operators

Bahareh Tolooshams, Ailsa Shen, Animashree Anandkumar

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Pennsylvania StateMechanistic interpretability

SASA: Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

Seyed Arshan Dalili, Mehrdad Mahdavi

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Clinical IntelligenceDisney Research, Disney ResearchHill ResearchMechanistic interpretability

Matched-Control Tests of Partition-Source Claims in One Routed Distillation Family

Bob Li, Chloe Cao, Constance Liu

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 0/5
medium 1/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026MATSMonashMechanistic interpretability

What does a Bayes-filtered transformer believe? A predictive Monte Carlo approach

Afiq Abdillah Effiezal Aswadi, Haotong Ma, Susan Wei

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U ChicagoU Chicago; University of CaliforU Chicago, Santa Fe Institute, GMechanistic interpretability

Introspection Tools Help LLMs Understand and Control Themselves

Xiao Liu, Junsol Kim, Shiyang Lai, Jacy Anthis and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026ACS ResearchCharles University Ovocný trh 5ACS Research, CharlesCharles University PragueU TorontoMechanistic interpretability

Think about how AIs think about themselves

Raymond Douglas, Jan Kulveit, Ondřej Havlíček, Theia Pearson-Vogel and 1 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NortheasternU SussexMechanistic interpretability

Claims of AI emergence should be grounded in information decomposition

Christoph Riedl, Fernando Rosas

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026School of Engineering and ApplieGoogle DeepMind via AdeccoMechanistic interpretability

The parameters in weight-sparse transformers are interpretable

Arnau Marin-Llobet, Stefan Heimersheim

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Massachusetts Institute of TechnU ChicagoMechanistic interpretability

Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models

Eric So, Alex Imas

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SoochowRenmin University of ChinaTongjiAustralian NationalMechanistic interpretability

Reading Attribution from Attention: Evidence Heads as Latent Attribution Mechanisms in LLMs

Qi Wu, Jianfeng Qu, Peng-Fei Zhang, Yanzhe Ji and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Massachusetts Institute of TechnHarvardHarvardMechanistic interpretability

Algorithmic Impact Reveals the Hidden Structure of Alignment

Zachary Wojtowicz, Michelle Si, Finale Doshi-Velez, Ariel Procaccia

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026StanfordPekingMechanistic interpretability

Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks

Jia Liang, Liangming Pan

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Vanderbilt University Medical CeMechanistic interpretability

Specialist Mediators: Causal Localization of Dense Fine-Tuning

Amir Asiaee

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
Show 20 more papers