Scholar
Zhengfu He
Google Scholar ID: mou-vPwAAAAJ
Shanghai Innovation Institute
Mechanistic Interpretability
Large Language Models
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
699
H-index
9
i10-index
9
Publications
14
Co-authors
0
Publications
6 items
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
2026
Cited
0
Tracing the Thought of a Grandmaster-level Chess-Playing Transformer
2026
Cited
0
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
2025
Cited
0
Evolution of Concepts in Language Model Pre-Training
2025
Cited
0
Attention Layers Add Into Low-Dimensional Residual Subspaces
2025
Cited
0
Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
2025
Cited
0
