© 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. 32561
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    zzo
    -0.08
    /of
    -0.08
    arily
    -0.08
    /ion
    -0.08
     ãĥŃãĥ¼
    -0.07
    ØŃÙģ
    -0.07
     кажд
    -0.07
    ниÑĩ
    -0.07
    umente
    -0.07
    gow
    -0.07
    POSITIVE LOGITS
    çļĦ
    0.14
    nya
    0.11
    ÑģÑı
    0.11
    çļĦãģ«
    0.10
    ÛĮ
    0.10
    à¯ģ
    0.09
    çļĦãģª
    0.09
    ìĿĦ
    0.09
    大åı¯
    0.08
    ious
    0.07
    Activations Density 0.003%

    No Known Activations