© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3495
    Prev
    Next
    INDEX
    Explanations

    invitations and proposals

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dota
    -0.22
     me
    -0.22
    sprites
    -0.22
    -upper
    -0.22
    doÄŁ
    -0.20
    ={()=>
    -0.20
    æĪij
    -0.20
    ç¾ķ
    -0.20
     addObserver
    -0.20
    obao
    -0.19
    POSITIVE LOGITS
     },↵↵↵
    0.21
     below
    0.21
    .openConnection
    0.20
    orgetown
    0.19
     here
    0.19
    ('<?
    0.19
    here
    0.18
    ici
    0.18
     btnSave
    0.18
    èijĨ
    0.18
    Activations Density 0.297%

    No Known Activations