© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4070
    Prev
    Next
    INDEX
    Explanations

    code programming

    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
    roken
    -0.28
    unken
    -0.26
    uraa
    -0.25
    fortunate
    -0.24
    urma
    -0.24
    poons
    -0.24
    ä¸ŃåĽ½ç½ij游
    -0.24
    "<?
    -0.23
    -expanded
    -0.23
    !!");↵
    -0.23
    POSITIVE LOGITS
    æĪĺçķ¥å¸ĥå±Ģ
    0.20
    let
    0.20
    ä¸ĢåIJį
    0.20
    ella
    0.20
    è´´åIJ§
    0.20
    åĤ¨èĵĦ
    0.19
     veter
    0.19
    å¸ĸåŃIJ
    0.19
     avalia
    0.18
     lineman
    0.18
    Activations Density 0.079%

    No Known Activations