© 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. 49771
    Prev
    Next
    INDEX
    Explanations

    numbers: 1, 3

    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
    elter
    -0.08
    æīijéĿ¢
    -0.07
    esti
    -0.07
    elmet
    -0.07
    ä¸Ĭ马
    -0.06
    jang
    -0.06
    å°¼æĸ¯
    -0.06
    _CANCEL
    -0.06
    -bind
    -0.06
    inig
    -0.06
    POSITIVE LOGITS
    beck
    0.12
    isters
    0.08
    ëĭĪëĭ¤
    0.07
    غاÙĦ
    0.07
    ساء
    0.07
    gal
    0.07
    å§Ķåijĺä¼ļ主任
    0.07
    zano
    0.07
    agas
    0.07
    æIJĸ
    0.07
    Activations Density 0.014%

    No Known Activations