l

🥭

Mejdi Sadriu

ProposalGrant

Closes May 18th, 2026

$0raised

$500minimum funding

$1,700funding goal

Offer to donate

8 daysleft to contribute

You're pledging to donate if the project hits its minimum goal and gets approved. If not, your funds will be returned.

José Wheeler

Identifying and auditing reasoning circuits in LLMs within Algoverse 2026 using Sparse Autoencoders (SAEs).

$0 / $2K

Matthew Farr

Probing possible limitations and assumptions of interpretability | Articulating evasive risk phenomena arising from adaptive and self modifying AI

$0 raised

Aditya Raj

Current LLM safety methods—treat harmful knowledge as removable chunks. This is controlling a model and it does not work.

$0 raised

Lucy Farnik

6-month salary for interpretability research focusing on probing for goals and "agency" inside large language models

$1.59K raised