© 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. 3170
    Prev
    Next
    INDEX
    Explanations

    resistance

    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
    æĶ¯çº¿ä»»åĬ¡
    -0.21
     jihadists
    -0.20
    exampleInputEmail
    -0.20
    ursal
    -0.19
    FetchRequest
    -0.19
    cheiden
    -0.19
     perish
    -0.19
     Helm
    -0.18
    appName
    -0.18
     hel
    -0.18
    POSITIVE LOGITS
     Erectile
    0.27
    Resistance
    0.24
     resist
    0.23
    ;};↵
    0.23
     resistance
    0.23
    /Dk
    0.22
    ufs
    0.21
    egen
    0.21
    *);↵↵
    0.21
    ://%
    0.21
    Activations Density 0.341%

    No Known Activations