© 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. 43220
    Prev
    Next
    INDEX
    Explanations

    finding solutions or alternatives

    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
    าà¸Ĺ
    -0.07
    ä¹ŁåIJĮæł·
    -0.07
    ä¸İæľ¬ç«Ļ
    -0.07
    å±ĤéĿ¢ä¸Ĭ
    -0.07
    次ä¼ļè®®
    -0.07
     ê²½ìļ°ìĹIJëĬĶ
    -0.07
    èĩªçĦ¶èĢĮçĦ¶
    -0.07
    æľ¬å°ı说
    -0.07
    otify
    -0.07
    !");
    -0.06
    POSITIVE LOGITS
    -ish
    0.08
    _projection
    0.07
    hada
    0.06
    cina
    0.06
    idez
    0.06
    hal
    0.06
     [](
    0.06
    [__
    0.06
    éĶ¦æłĩ
    0.06
     оÑĤноÑģ
    0.06
    Activations Density 0.036%

    No Known Activations