Bartosz Cywiński

bcywinski

·

https://cywinski.github.io/

AI & ML interests

Mechanistic Interpretability

Recent Activity

updated a model 14 days ago

bcywinski/jacobian-lens-qwen3.5-9b

published a model 25 days ago

bcywinski/jacobian-lens-qwen3.5-9b

updated a dataset 26 days ago

bcywinski/msm-packaging-aft-setA-activations

View all activity

Organizations

None yet

commented a paper about 1 year ago

Eliciting Secret Knowledge from Language Models

Paper • 2510.01070 • Published Oct 1, 2025 • 6 •

commented 2 papers over 1 year ago

Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Paper • 2505.14352 • Published May 20, 2025 • 9 •

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Paper • 2501.18052 • Published Jan 29, 2025 • 8 •