© 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. 1186
    Prev
    Next
    INDEX
    Explanations

    code fragments

    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
     tremend
    -0.31
     enthus
    -0.30
    çļĦ带é¢Ĩ
    -0.30
     dames
    -0.28
     culo
    -0.28
     Playoff
    -0.27
     oro
    -0.26
     cunt
    -0.26
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.25
    ãĥµ
    -0.25
    POSITIVE LOGITS
    rades
    0.26
    ifr
    0.25
     /*
    0.24
    æĥ®
    0.24
    lrt
    0.24
     if
    0.24
    "<?
    0.24
    :maj
    0.23
     //
    0.23
    è¹ģ
    0.23
    Activations Density 1.238%

    No Known Activations