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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 619
    Prev
    Next
    INDEX
    Explanations

    say ","

    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
    ;/*
    -0.32
    ;!
    -0.29
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.25
    ,:);↵
    -0.25
    +offset
    -0.24
    ;r
    -0.23
    ä»Ģ麽
    -0.23
    ToShow
    -0.22
    __,__
    -0.22
    +":
    -0.22
    POSITIVE LOGITS
    ,
    0.69
    ï¼Į
    0.52
    ï¼Įåľ¨
    0.50
    ØĮ
    0.44
    ï¼Įé»ĺ认
    0.38
    ï¼Į请
    0.37
    ï¼ĮãĢĬ
    0.31
    ï¼ĮåĪĻ
    0.31
    ï¼Į并
    0.30
    ä¸Ģèĩ´å¥½è¯Ħ
    0.30
    Activations Density 3.166%

    No Known Activations