{"total":52,"rows":[{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115,"area":"mechinterp"},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51,"area":"mechinterp"},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2505.17117","title":"From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning","created":"2025-05-21","cited_by_count":25,"area":"lr"},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2501.06254","title":"Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words","created":"2025-01-09","cited_by_count":18,"area":"lr"},{"id":"2412.17626","title":"Tracking the Feature Dynamics in LLM Training: A Mechanistic Study","created":"2024-12-23","cited_by_count":16,"area":"mechinterp"},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2603.09972","title":"From Data Statistics to Feature Geometry: How Correlations Shape Superposition","created":"2026-03-10","cited_by_count":10,"area":"mechinterp"},{"id":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7,"area":"mechinterp"},{"id":"2506.18141","title":"Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models","created":"2025-06-22","cited_by_count":6,"area":"mechinterp"},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.11881","title":"From Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders","created":"2026-02-12","cited_by_count":6,"area":"mechinterp"},{"id":"2505.15970","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","created":"2025-05-21","cited_by_count":5,"area":"mechinterp"},{"id":"2505.20435","title":"The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology","created":"2025-05-26","cited_by_count":5,"area":"safety"},{"id":"2502.01628","title":"Harmonic Loss Trains Interpretable AI Models","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2505.15811","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2508.00331","title":"Embryology of a Language Model","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2506.15617","title":"The Compositional Architecture of Regret in Large Language Models","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2506.16975","title":"Latent Concept Disentanglement in Transformer-based Language Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2504.20197","title":"Representation Learning on a Random Lattice","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2605.23035","title":"Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography","created":"2026-05-21","cited_by_count":2,"area":"alignment"},{"id":"2502.03618","title":"The Logical Implication Steering Method for Conditional Interventions on Transformer Generation","created":"2025-02-05","cited_by_count":1,"area":"mechinterp"},{"id":"2505.17071","title":"What's in a prompt? Language models encode literary style in prompt embeddings","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.22572","title":"Fusion Steering: Prompt-Specific Activation Control","created":"2025-05-28","cited_by_count":1,"area":"mechinterp"},{"id":"2512.06655","title":"Graph-Regularized Sparse Autoencoders for LLM Safety Steering","created":"2025-12-07","cited_by_count":1,"area":"safety"},{"id":"2601.03570","title":"How Do Large Language Models Learn Concepts During Continual Pre-Training?","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2602.13524","title":"Singular Vectors of Attention Heads Align with Features","created":"2026-02-13","cited_by_count":1,"area":"mechinterp"},{"id":"2605.09887","title":"The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws","created":"2026-05-11","cited_by_count":1,"area":"mechinterp"},{"id":"2606.02061","title":"Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design","created":"2026-06-01","cited_by_count":1,"area":"mechinterp"},{"id":"2606.18322","title":"SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior","created":"2026-06-16","cited_by_count":1,"area":"mechinterp"},{"id":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.20596","title":"Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects","created":"2026-07-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.24645","title":"Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects","created":"2026-07-27","cited_by_count":1,"area":"mechinterp"},{"id":"2609.05575","title":"Capsule Lens: Locating and Tracking Concept Geometry in Model Representations","created":"2026-09-04","cited_by_count":1,"area":"mechinterp"},{"id":"2505.00190","title":"Empirical Evaluation of Progressive Coding for Sparse Autoencoders","created":"2025-04-30","cited_by_count":0,"area":"mechinterp"},{"id":"2505.22506","title":"Sparsification and Reconstruction from the Perspective of Representation Geometry","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2510.04285","title":"Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.18756","title":"Towards Understanding the Robustness of Sparse Autoencoders","created":"2026-04-20","cited_by_count":0,"area":"safety"},{"id":"2604.23829","title":"Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features","created":"2026-04-26","cited_by_count":0,"area":"mechinterp"},{"id":"2605.06494","title":"From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.08954","title":"MolWorld: Molecule World Models for Actionable Molecular Optimization","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.14347","title":"Exemplar Partitioning for Mechanistic Interpretability","created":"2026-05-14","cited_by_count":0,"area":"safety"},{"id":"2607.10578","title":"Laguerre Geometry for Interpreting Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36294","title":"When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.37731","title":"Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}