Causal Interpretability

Follow this topic Ask about this topic

Causal interpretability asks not just what information a model represents, but what changes its behavior when that information or a component is altered. Researchers use activation patching and ablation, causal mediation, sparse autoencoders, circuit discovery, and counterfactual feature attribution to trace effects through models. These approaches are applied to language-model reasoning, vision and multimodal systems, and scientific or time-series predictors. A central challenge is showing that an explanation reflects the mechanism used on natural inputs: a feature can be easy to decode without affecting the output, and causal conclusions depend on intervention design, assumptions, and robustness checks.

Latest papers

107 papers7 papers in the last four weeks, down 22% on the four weeks before. 0.0% of all new papers.

On Reasoning Correctness Directions
Oct 18, 2026Munachiso Samuel Nwadike, Zayd M. K. Zuhri, Rifo Genadi +5Causal Interpretability Activation Steering
MBZUAI, UAE · RIKEN AIP, Japan · Mila, Canada +1
World Model Interpretability: From Decoding Representations to Understanding Latent Worlds
Oct 18, 2026Jize Wang, Yongcheng Jing, Xinyi Le +3World Models Latent World Models
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University · College of Computing and Data Science, Nanyang Technological University
Explaining Heterogeneous Treatment Effects with Causal Forests and the Hoeffding Functional Decomposition
Oct 12, 2026Gaëtan Patinier, Clément Bénard, Margaux TörnqvistCausal Effect Estimation Causal Interpretability
Theremia · Thales cortAIx-Labs
Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models
Oct 2, 2026Sankaran Vaidyanathan, Rafal Urbaniak, Emily Bunnapradist +2Circuits in Language Models Mechanistic Interpretability
Basis Research Institute · University of Massachusetts Amherst · MIT
Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions
Sep 30, 2026Beiming Liu, Minjie ChenCircuits in Language Models Causal Interpretability
PetroChina Southwest Oil and Gasfield Company, China
Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable
Sep 28, 2026Or Shafran, Mor GevaCausal Interventions in Language Models Causal Interpretability
Blavatnik School of Computer Science and AI, Tel Aviv University
Small transformers track Bayesian evidence for latent common causes via a context-invariant mechanism
Sep 28, 2026Amir Mohammadpour, Michael FrankeBayesian Inference Causal Reasoning in Language Models
Department of Linguistics, University of Tübingen
What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation
Sep 26, 2026Arshia Eftekhari zadehLLM Interpretability Faithfulness of Language Model Explanations
School of Electrical and Computer Engineering University of Tehran, Tehran, Iran
Certifying Interventional Agreement Among Observationally Equivalent Causal Models
Sep 26, 2026Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1Causal Inference Causal Intervention
Toronto Metropolitan University · Flybits Labs, Creative AI Hub · MIT Media Lab, Massachusetts Institute of Technology
Are Stated Reasoning Steps Causally Load-Bearing?
Sep 22, 2026Abhiram Bhupatiraju, Rayan NyaupaneCoT Faithfulness LLM Auditing
The University of Texas at Austin
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
Sep 19, 2026Qianli Wang, Yilong Wang, Dennis Wei +5CoT Faithfulness LLM Interpretability
Technische Universität Berlin · German Research Center for Artificial Intelligence (DFKI) · IBM Research +4
Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
Sep 19, 2026Weihan Li, Xinlei Chen, Yuhan Song +2Language Model Steering LLM Interpretability
The University of Tokyo · Harbin Institute of Technology, Shenzhen · The Hong Kong University of Science and Technology
Splitting the Difference: Interpretable Causal Forests for Treatment Effect Heterogeneity and Bias
Sep 15, 2026Nicolas Alexander Ihlo, Merle BehrCausal Effect Estimation Conditional Average Treatment Effect Estimation
Faculty of Informatics and Data Science University of Regensburg, Germany
Calibrating Interpretability Instruments Before Trusting Their Verdicts
Sep 13, 2026Orion Reblitz-RichardsonLLM Interpretability Causal Interpretability
Distiller Labs
PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders
Sep 7, 2026Nandita N. Patil, Eshwar R. A., Gajanan V. HonnavarMechanistic Interpretability Causal Interpretability
QuaNad Research Laboratory, PES University, Bengaluru, India · Independent Researcher, QNu Labs Pvt Ltd, Bengaluru, India. Former Professor at PES University (EC Campus), Bengaluru
Lagged Coupling: Internal Representations Become Readable Before They Become Causal
Sep 1, 2026Xining XunCausal Interpretability Causal Interventions in Language Models
Tsingjiao Information Science (Beijing) Co., Ltd.
Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit
Aug 27, 2026Sai Adith Senthil KumarMechanistic Interpretability Circuits in Language Models
George Mason University
Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit
Aug 26, 2026Anqi Peter LiNeural Network Interpretability Causal Interventions in Language Models
Substrate Labs
Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution
Aug 25, 2026Yijun Liao, Fanwei LiangShortcut Learning Causal Interpretability
Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
Aug 19, 2026Vijay ErramilliMechanistic Interpretability Transformer Interpretability
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
Aug 13, 2026Dekun YangHidden-State Probing State Representation Learning
Zhejiang University
CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence
Aug 12, 2026Michael Georgiades, Charalambia VarnavaFeature Attribution Causal Attribution
Department of Computer Science Neapolis University Pafos Cyprus · CaSToRC The Cyprus Institute Nicosia, Cyprus
Spatial Attention Noise Masking for Causally Sufficient Interpretability
Aug 12, 2026Benjamin Formby, Kuang-Ching Wang, D Hudson SmithExplainable Image Classification Causal Interpretability
Electrical and Computer Engineering department at Clemson University, Clemson, SC · School of Computing at Binghamton University, Binghamton, NY · Department of Mathematical and Statistical Sciences at Clemson University, Clemson, SC
Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library
Aug 12, 2026Xining XunCausal Representation Learning LLM Auditing
Tsingjiao Information Science (Beijing) Co., Ltd.
Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation
Aug 4, 2026Shashwat Sourav, Subhadeep Pal, Markus J. Buehler +4LLM Reasoning with Graphs Scientific Hypothesis Generation
Department of Physics, Washington University in St. Louis · Oak Ridge National Laboratory · Lawrence Berkeley National Laboratory +6
GENESIS: Towards Explainable Causal Discovery
Aug 4, 2026Abhinav Thorat, Ravi Kumar Kolla, Vishak K Bhat +2Causal Discovery Causal Structure Learning
User Engagement Research, Sony Research India
Understanding Online Failure Prediction in Linux Through Complementary Multi-View Explainability
Aug 1, 2026Diogo Dória, João R. CamposFault Detection Causal Interpretability
University of Coimbra, CISUC/LASI Department of Informatics Engineering Coimbra, Portugal
Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?
Jul 31, 2026Xining XunCausal Discovery Causal Reasoning in Language Models
Tsingjiao Information Science (Beijing) Co., Ltd.
Same Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model States
Jul 29, 2026Weiyi Kong, Zhuoran LiCausal Reasoning in Language Models Causal Inference
University of Toronto, Toronto, Canada · The University of Hong Kong, Hong Kong
From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios
Jul 28, 2026Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1Feature Attribution Causal Attribution
Hologen AI London, UK · Mathematics Research Centre Academy of Athens Athens, GR · FAU Erlangen Nuremberg Imperial College London Erlangen, DE & London, UK +1

Oct 18, 2026J/K move · Enter open · S save

On Reasoning Correctness Directions

Munachiso Samuel Nwadike, Zayd M. K. Zuhri, Rifo Genadi, Abzal Nurgazy+4

MBZUAI, UAE · RIKEN AIP, Japan · Mila, Canada+1

Causal Interpretability Activation Steering Causal Interventions in Language Models

Open paper AskPDF arXiv

We present experimental evidence suggesting that information about whether a model's reasoning is on the right track can be linearly decodable without defining a causally useful direction for steering. To study this, we introduce ChainSearch, a controlled arithmetic reasoning task that extends Countdown with explicit search and backtracking. We train a 3-million-parameter model to solve this task. Its compact size allows us to study internal model correctness directions in detail using linear probes, mean activation differences, and direct optimisation, as part of a rigorous search for internal reasoning-correctness directions. We find that while the model contains statistically significant internal directions of reasoning correctness, none of the resulting directions consistently improves reasoning under causal intervention. This calls into question whether the linear representation hypothesis is sufficient for identifying causally useful directions in the context of reasoning. Our code is made available together with this work.