Re:Astra can read and write weights to improve Qwen
by ninjahawk1 on Monday November 02, 2026 @06:32PM
(#50345731)
The potential implications in mech interp of this are enormous. What if we can use frontier models to isolate harmful behaviors?
I was talking to someone from UCL and he said that there was a recent paper that proposed that only 10% (I think) of model neurons are non-polysemantic. I really think mech interp might be on the verge of a breakthrough.
We have all these different pieces of knowledge about model internals but it’s like we haven’t connected them yet.
I was talking to someone from UCL and he said that there was a recent paper that proposed that only 10% (I think) of model neurons are non-polysemantic. I really think mech interp might be on the verge of a breakthrough.
We have all these different pieces of knowledge about model internals but it’s like we haven’t connected them yet.