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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3582
    Prev
    Next
    INDEX
    Explanations

    dates and pages

    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
    ADER
    -0.22
    almö
    -0.21
    .nlm
    -0.21
    toupper
    -0.21
    éĹªè¿ĩ
    -0.20
    subpackage
    -0.20
    /effects
    -0.20
    æĸ°æµªè´¢ç»ı
    -0.20
    被èªī
    -0.19
     ++;↵
    -0.19
    POSITIVE LOGITS
    뾸
    0.20
    RESSED
    0.19
     Katz
    0.19
    é¼¹
    0.19
    ione
    0.18
    OCKET
    0.18
    quil
    0.18
    atti
    0.18
     Drops
    0.17
    ...');↵
    0.17
    Activations Density 0.001%

    No Known Activations