Mechanistic Interpretability

Ask about this topic

Momentum

20 papers in the last four weeks, up 54% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 175

All topics
CardsList

  1. Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability

    Oct 1, 2026Chuqin Geng, Li Zhang, Haolin Ye +3Mechanistic InterpretabilityModel Discovery

    University of Toronto · McGill University

  2. Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models

    Oct 1, 2026Tido Specht, Elias Benedict Krey, Nils Neukirch +1Large Language Model AlignmentMultimodal Large Language Models

    University of Groningen · Carl von Ossietzky University of Oldenburg

  3. When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task

    Sep 29, 2026Sai Sumedh R. Hindupur, Hadas Orgad, Thomas Fel +1Multilayer PerceptronsMechanistic Interpretability

    School of Engineering and Applied Science, Harvard University · Kempner Institute, Harvard University · Goodfire AI

  4. From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

    Sep 29, 2026Jiayuan Chen, Botao Yu, Tianyu Liu +3PhenotypesCells

    Department of Computer Science and Engineering, The Ohio State University · Department of Biomedical Informatics, The Ohio State University · Department of Biostatistics, Yale University +1

  5. Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?

    Sep 28, 2026Li Zhang, Chuqin Geng, Mark Zhang +4Mechanistic InterpretabilityCircuits

    University of Toronto · McGill University · Tsinghua University

  6. Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability

    Sep 28, 2026Xu Wang, Difan Zou, Xuansheng WuSycophancyRefusals

    The University of Hong Kong · Shenzhen Loop Area Institute · Shanghai Artificial Intelligence Laboratory

  7. From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features

    Sep 28, 2026Dewen Liu, Zixuan Li, Jonathan Pan +4Mechanistic InterpretabilityModel Activations

    Tsinghua University · Fudan University · University of Edinburgh

  8. Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders

    Sep 28, 2026Zichao Yu, Qianshuo Ye, Xu Wang +1Efficient On-Policy DistillationOnline-Policy Distillation

    School of Computing and Data Science, The University of Hong Kong · Department of Computer Science and Technology, University of Cambridge · Shenzhen Loop Area Institute

  9. On Temporal Binding in Large Audio Language Models

    Sep 28, 2026Paul Primus, Gerhard WidmerLarge Audio Language ModelsMechanistic Interpretability

    Institute of Computational Perception, Johannes Kepler University Linz, Austria · LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria

  10. Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons

    Sep 24, 2026Huseyin Cavus, Sebin Sabu, Joshua Spear +2Generative HallucinationNeurons

    Trakya University, Edirne, Türkiye · DRIVE, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK

  11. Stream Recursion Model (SRM)

    Sep 23, 2026Asael Sorensen, Charles Brock, David Chamberlain +3Mechanistic InterpretabilityRecursive Models

    Sandia National Laboratories, Albuquerque, NM, USA · Institute for Complex Additive Systems Analysis, New Mexico Institute of Mining and Technology, Socorro, NM, USA · Department of Computer Science and Engineering, New Mexico Institute of Mining and Technology, Socorro, NM, USA.

  12. Matryoshka attribution: Learning to attribute language model outputs to representations and weights

    Sep 22, 2026Aryaman Arora, Kirill Acharya, Nathan Hu +4Mechanistic InterpretabilityModel Activations

    Stanford University

  13. Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders

    Sep 21, 2026Rithin Nagaraj, Rupa Laalasa Oruganti, Prerna Subhashchandra Kunder +1Transformer ArchitecturesTransformer Attention

    Department of Computer Science and Engineering PES University Bangalore, India

  14. Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

    Sep 21, 2026Gautam Ranka, Shubham Santosh Pandere, Aiden DsouzaMechanistic InterpretabilityNeurons

    IvLabs, VNIT Nagpur, India.

  15. Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs

    Sep 20, 2026Edward G. Friedman, Xiangchen SongCircuitsMechanistic Interpretability

    School of Computer Science Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213

  16. Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles

    Sep 17, 2026Noah Mamié, Laurin van den BerghProfileTransparency

    University of Zurich Department of Informatics

  17. The Misery of Mechanistic Interpretability: A Formal Perspective

    Sep 14, 2026Tobias Ladner, Matthias AlthoffMechanistic InterpretabilityInterpretability

    Technical University of Munich, Germany

  18. Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)

    Sep 14, 2026Christian Fisch, Angela Altmeier, Martin Obschonka +2Mechanistic InterpretabilityDial

    Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg, 1855, Luxembourg · Amsterdam Business School, University of Amsterdam, Amsterdam, 1018 TV, The Netherlands · Stanford Graduate School of Business, Stanford University, Stanford, CA 94305, USA

  19. What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track

    Sep 14, 2026Lingheng Du, Yiming Tang, Xufeng Duan +1Large Language Model Reinforcement LearningImproving Sparse Autoencoders

    Peking University · National University of Singapore · The Chinese University of Hong Kong

  20. On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing

    Sep 7, 2026Yuval Koren, Assaf Ben-Kish, Raja Giryes +2Dense Associative MemoryFactual Recall

    Blavatnik School of Computer Science and AI, Tel Aviv University

  21. Large Language Models in Resolving Contextual Knowledge Conflicts

    Sep 2, 2026Xinye Yang, Zhenyang Liu, Ruisi Li +1LLM Reasoning StrategiesReasoning Skills

    1Northwestern University, Evanston, IL · 2New York University, New York, NY · 3Computer & Information Science and Engineering, University of Florida, Gainesville, FL

  22. ObserverBench: Testing Mechanistic Estimates for Intervention and Control

    Sep 2, 2026Vijay ErramilliMechanistic InterpretabilitySafety Benchmarks

  23. S^3martCirc: Self-supervised Smart Circuit Discovery

    Sep 1, 2026Wendy Zheng, Yinhan He, Liang Wu +1Mechanistic InterpretabilityCircuits

    University of Virginia · Nokia

  24. MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines

    Aug 31, 2026Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5InterpretabilityMechanistic Interpretability

    Ubiquitous Knowledge Processing (UKP) Lab, Technical University of Darmstadt, Germany · Cluster of Excellence “Reasonable Artificial Intelligence” (RAI), hessian.AI, Germany · National Research Center for Applied Cybersecurity ATHENE, Germany +1

  25. The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

    Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiJailbreaksJailbreak Attacks

    Department of Computer Science, Iowa State University, United States · Meta, United States

  26. RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons

    Aug 25, 2026Runyu Wang, Bo Liu, Xiaxin Zhang +6NeuronsMechanistic Interpretability

    School of Transportation and Civil Engineering, Nantong University · Chongqing University of Post and Telecommunications · China Southern Power Grid Company Limited +1

  27. Decoding Task Progress from VLA Representations

    Aug 13, 2026Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan +2Visuomotor PolicyMechanistic Interpretability

    Cornell University

  28. Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

    Aug 13, 2026Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8DissociationLinguistics

    Department of Computer Science and Engineering, University of South Carolina · Department of Communication Sciences and Disorders, University of South Carolina · ALLT.AI, LLC, Columbia, SC +3

  29. Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

    Aug 12, 2026Mengru Wang, Junfeng Fang, Shuofei Qiao +16Artificial Intelligence SafetyArtificial Intelligence Scientists

    Zhejiang University · National University of Singapore · Heriot-Watt University +3

  30. From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

    Aug 11, 2026Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10Trustworthy Artificial IntelligenceLarge Language Model Reliability

    Amazon AGI · Meta · Autodesk +3

  31. Measuring Semantic Abstractness of SAE Features via Nonlocality

    Aug 11, 2026Chuqiao Lin, Shivaji Sondhi, Xiao-Liang QiSparse Autoencoder FeaturesMechanistic Interpretability

    Rudolf Peierls Centre for Theoretical Physics, University of Oxford · Leinweber Institute for Theoretical Physics, Stanford University

  32. Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

    Aug 10, 2026Ashim Dhor, Pin-Yu ChenMechanistic InterpretabilityInterpretability

    1IISER Bhopal · 2IBM Research

  33. Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways

    Aug 10, 2026Shuyi Miao, Wangjie Qiu, Pengyang Shao +4Multilingual SafetyLarge Language Model Safety

    Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing · School of Artificial Intelligence, Beihang University, China · Zhongguancun Laboratory, Beijing, China +2

  34. Finding Usable Weight Mechanisms with Tiled SVD

    Aug 7, 2026Ash Manvi, Samreena TajreenSingular Value DecompositionMechanistic Interpretability

    Aquin Labs

  35. MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering

    Aug 6, 2026Jakub Poćwiardowski, Mateusz ModrzejewskiText-To-MusicText Generation

    Institute of Computer Science Warsaw University of Technology Warsaw, Poland

  36. Sparse Weight Decomposition for Efficient Circuit Extraction

    Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Transformer ArchitecturesModel Weights

    IQuest Research · Safe AI Forum · University of Oxford +2

  37. DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

    Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3Visual ReasoningRecent Vision-Language Models

    University of Electronic Science and Technology of China, Chengdu, China.

  38. Emergent Latent-State Computation under Stochastic Volatility

    Jul 28, 2026Xiaoyu Huang, Lulu WangLatent StatesIntermediate Latent States

    Department of Mathematics Temple University Philadelphia, PA, USA · Department of Data Analytics Dickinson College Carlisle, PA, USA

  39. Do LLMs Know Their Vulnerable Scenarios?

    Jul 26, 2026Ziheng Peng, Huiqi Deng, Haoran Jing +5Mechanistic Interpretability

    Xi’an Jiaotong University Shanghai, China · Shanghai Artificial Intelligence Laboratory Shanghai, China

  40. Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation

    Jul 25, 2026Gonzalo A. RuzRegulatory NetworksSurrogate Models

    Facultad de Ingenier´ıa y Ciencias, Universidad Adolfo Ib´a˜nez · Millennium Nucleus for Social Data Science (SODAS) · Millennium Nucleus in Data Science for Plant Resilience (PhytoLearning) +1

  41. Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

    Jul 25, 2026Dhruvil S, Fenil Sojitra, Ravirajsinh ChauhanMulti-Head AttentionDeepseek

    1Indian Institute of Technology Madras · 2P P Savani University

  42. From Hybrid Mechanistic--Data-Driven Modeling Toward Neuro-Symbolic AI: What, Why, and How

    Jul 24, 2026Moein E. Samadi, Andreas SchuppertNeuro-Symbolic FrameworkArtificial Intelligence Models

    Institute for Computational Biomedicine, RWTH Aachen University, Aachen, Germany. · Center for Computational Life Sciences, RWTH Aachen University, Aachen, Germany.

  43. Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry

    Jul 22, 2026Jason Y. Hu, Ivan Higuera-Mendieta, Patrick Obin Sturm +1Atmospheric DynamicsWireless Foundation Models

    Stanford University, Department of Computer Science, Stanford, CA, USA. · Stanford University, Department of Earth System Science, Stanford, CA, USA · University of Southern California, Department of Earth Sciences, Los Angeles, CA, USA +1

  44. Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

    Jul 20, 2026Katarzyna Filus, Sebastian PokucińskiMechanistic InterpretabilitySemantic Representations

    Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Bałtycka 5, 44-100 Gliwice, Poland · Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland

  45. Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs

    Jul 18, 2026Sharath Naganna, Tanvir Ahmed Sijan, Uddipta KalitaLarge Language Models FailMechanistic Interpretability

    Indian Institute of Technology Bombay, Mumbai, India · Jahangirnagar University, Dhaka, Bangladesh · National Institute of Technology, Silchar, India

  46. Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

    Jul 16, 2026Jihoon Hong, Julian Skifstad, Qiyue Dai +2World ModelsSteering

    Georgia Institute of Technology

  47. Transcoders for Investigating Deception in Language Models

    Jul 16, 2026Darius Lim, Nathan Leow, Xin Wei ChiaDeceptionMechanistic Interpretability

    Home Team Science & Technology Agency (HTX) Singapore

  48. Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions

    Jul 15, 2026Zachary IzzoNext-Token DistributionMechanistic Interpretability

    NEC Labs America

  49. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    Jul 14, 2026Ingmar Posner, Anson Lei, Bernhard SchölkopfModel DiscoveryMechanistic Interpretability

    Applied AI Lab., University of Oxford, United Kingdom. · MPI for Intelligent Systems & ELLIS Institute, Tübingen, Germany.

  50. Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

    Jul 13, 2026Zixiang Xu, Sixian Li, Huaxing Liu +4Llm-As-A-JudgeJudges

    AMAP, Alibaba Group · Mohamed bin Zayed University of Artificial Intelligence · University of Southern California +1

  51. Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

    Jul 9, 2026Bendegúz Váradi, Zoltán KmettyImproving Sparse AutoencodersBert-Based Models

    Centre for Social Sciences, CSS-RECENS Research Group, Budapest 1097, Hungary. · Department of Sociology, Faculty of Social Sciences, Eötvös Loránd University, Budapest, Hungary.

  52. Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

    Jul 9, 2026Amir AsiaeeInterpretabilityMechanistic Interpretability

    Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37232, USA

  53. Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

    Jul 8, 2026Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1Large Language Model JailbreaksAdversarial Prompts

    Department of Computer Science, University of South Dakota, USA · School of Information and Artificial Intelligence, Yangzhou University, Yangzhou, China

  54. Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning

    Jul 8, 2026Pranav Sawant, Jakub KrejčíMechanistic InterpretabilityExplainable Artificial Intelligence

    The University of Texas at Dallas 800 W Campbell Rd, Richardson, TX 75080, United States · VSB—Technical University of Ostrava 708 00, Ostrava, Czech Republic

  55. Latent Programming Horizons in Coding Agents

    Jul 6, 2026André Silva, Han Tu, Martin MonperrusCoding AgentsMechanistic Interpretability

    KTH Royal Institute of Technology Stockholm, Sweden

  56. Individual Parameters in Weight-Sparse Transformers Appear Interpretable

    Jul 3, 2026Arnau Marin-Llobet, Stefan HeimersheimMechanistic InterpretabilityModel Weights

    School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138

  57. Towards Robustness against Typographic Attack with Training-free Concept Localization

    Jul 2, 2026Bohan Liu, Wenqian Ye, Guangzhi Xiong +3Contrastive Language-Image Pre-Training ModelVision Transformer

    University of Virginia, Charlottesville VA 22903, USA

  58. Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

    Jul 2, 2026Zhiren Gong, He Lu, Tiantong Wang +6AblationTransformer Architectures

    College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

  59. Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

    Jul 2, 2026Rodrigo Mendoza-SmithImproving Sparse AutoencodersIntermediate Decoder Layers

    Independent Researcher.

  60. Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

    Jul 1, 2026Zihao Qi, Christopher EarlsQubitMechanistic Interpretability

    Department of Physics, Cornell University, Ithaca, NY 14853, USA. · Center for Applied Mathematics, Cornell University, Ithaca, NY 14853, USA.