© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9696
    Prev
    Next
    INDEX
    Explanations

    string type annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.08
    ment
    -0.07
    ity
    -0.07
    ier
    -0.07
    df
    -0.07
    sert
    -0.07
    caras
    -0.06
    reak
    -0.06
    менов
    -0.06
    ×Ķ׾
    -0.06
    POSITIVE LOGITS
    .fromCharCode
    0.08
    DBus
    0.07
    ìį¨
    0.07
    onaut
    0.07
    å¿ĥäºĨ
    0.07
    à¸Ħม
    0.07
    rita
    0.07
    ×Ļ×ķ
    0.07
    punt
    0.07
    bonne
    0.07
    Activations Density 0.023%

    No Known Activations