© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    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
    )){↵↵
    -0.31
    ,},↵
    -0.27
    TOTYPE
    -0.23
    ":"'
    -0.21
    sworth
    -0.20
    æł¡
    -0.20
    alse
    -0.20
     TMPro
    -0.20
    ;};↵
    -0.20
    ç»ıå¼Ģ
    -0.19
    POSITIVE LOGITS
    ">ÃĹ</
    0.23
    venge
    0.21
    å¾Ĥ
    0.20
    .uml
    0.20
    诩
    0.20
     Randolph
    0.19
     verdienen
    0.19
    ãĥŀãĥ³ãĤ·ãĥ§ãĥ³
    0.19
    -nil
    0.18
     apiUrl
    0.18
    Activations Density 0.001%

    No Known Activations