© 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. 4141
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    Negative Logits
    cased
    -0.20
    inement
    -0.20
    é¢Ŀ
    -0.19
    误ä¼ļ
    -0.19
    achie
    -0.19
    azzo
    -0.18
    phe
    -0.18
    ç§ijåĪĽ
    -0.18
    ="'.
    -0.18
    presso
    -0.18
    POSITIVE LOGITS
    rescia
    0.21
    \xaa
    0.21
    łģ
    0.20
    AdapterFactory
    0.19
    ãĥ¡ãĥ¼ãĤ
    0.18
    importe
    0.18
    ÙħجÙħÙĪعة
    0.18
     ragazzi
    0.18
    MET
    0.18
    /inet
    0.17
    Activations Density 0.001%

    No Known Activations