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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1231
    Prev
    Next
    INDEX
    Explanations

    U.S. patent numbers

    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
    omore
    -0.23
    TouchUpInside
    -0.22
    ylko
    -0.22
    (strtolower
    -0.21
    ennifer
    -0.21
    .executeUpdate
    -0.20
    alsy
    -0.20
    .optString
    -0.20
    yssey
    -0.20
    ingleton
    -0.20
    POSITIVE LOGITS
     Marketable
    0.29
     Closet
    0.24
     Decorating
    0.24
     Wrest
    0.23
    oriously
    0.23
     tatto
    0.23
    strtotime
    0.23
    roupon
    0.23
     Gorgeous
    0.22
    ä½Ĩä¸įéĻIJ
    0.22
    Activations Density 0.340%

    No Known Activations