© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14953
    Prev
    Next
    INDEX
    Explanations

    % TAG

    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
    ä½Ĩä¸įè¦ģ
    -0.07
    ë¡
    -0.07
    ále
    -0.07
    itäts
    -0.07
    å°ĶèĴĻ
    -0.07
     raya
    -0.07
    æĢ§å¥½
    -0.07
    à§įড
    -0.07
    /../
    -0.07
    /entities
    -0.07
    POSITIVE LOGITS
    ftime
    0.07
    -quote
    0.07
    _latest
    0.07
    +",
    0.06
     REPLACE
    0.06
    佬
    0.06
    é¢
    0.06
    طر
    0.06
    aip
    0.06
    thers
    0.06
    Activations Density 0.001%

    No Known Activations