© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 301
    Prev
    Next
    INDEX
    Explanations

    saying

    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
    æĬ¥å¤į
    -0.22
    )set
    -0.19
     jus
    -0.19
     AppBundle
    -0.19
     deeply
    -0.19
     ("-
    -0.19
    åijĥ
    -0.18
    pageTitle
    -0.18
    stantial
    -0.18
    ARIANT
    -0.18
    POSITIVE LOGITS
    é¦IJ
    0.27
    matchCondition
    0.27
     Interracial
    0.26
    çĽijåIJ¬é¡µéĿ¢
    0.25
     diseñador
    0.25
    ););↵
    0.25
    upertino
    0.25
    }());↵
    0.24
    emodel
    0.23
    åĻĻ
    0.23
    Activations Density 2.015%

    No Known Activations