© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    code and foreign text

    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
    ç£Ĭ
    -0.22
    女ãģ®
    -0.21
     ApplicationException
    -0.20
    cade
    -0.20
    findById
    -0.19
     '".$
    -0.19
    _KIND
    -0.19
    æĥ¹
    -0.19
    OMETRY
    -0.18
    FLAG
    -0.18
    POSITIVE LOGITS
    æĦ«
    0.24
    广åijĬæľįåĬ¡
    0.22
    ä½ľèĢħæīĢæľī
    0.21
    Serviço
    0.20
    å¾Īå¤ļçݩ家
    0.20
    innacle
    0.20
    .createClass
    0.20
    ElementException
    0.19
    ButtonDown
    0.19
    ofday
    0.19
    Activations Density 0.002%

    No Known Activations