Michael Lan
3 papers · 2024–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
mechanistic interpretability
(2)
ai safety
(1)
model interpretability
(1)
circuit analysis
(1)
steering vector
(1)
model auditing
(1)
fine-tuned model
(1)
activation space
(1)
mechanistic analysis
(1)
backdoor removal
(1)
circuit interpretability
(1)
sequence continuation
(1)
model behavior prediction
(1)
neural network internal
(1)
autoencoder mappings
(1)
transformer architecture
(1)
refusal of harmful prompts
(1)
Papers
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
ACL 2026
Activation Space Interventions Can Be Transferred Between Large Language Models
ICML 2025
Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
EMNLP 2024