© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    code

    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
    å¼ĤæĢ§
    -0.19
     devil
    -0.19
    .Comparator
    -0.19
     ones
    -0.19
    ialect
    -0.19
    ellar
    -0.18
    .TXT
    -0.18
    ipher
    -0.18
    QWidget
    -0.18
    /english
    -0.18
    POSITIVE LOGITS
    /******/
    0.25
    åĽ½éĻħåľ¨çº¿
    0.23
    nqu
    0.22
    resas
    0.21
    ä¸ĭéĿ¢æĺ¯å°ı
    0.20
    stdexcept
    0.20
    é¢ĺ主
    0.19
    :Any
    0.19
    TimeString
    0.19
    vince
    0.19
    Activations Density 0.001%

    No Known Activations