© 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. 21985
    Prev
    Next
    INDEX
    Explanations

    parenthesizing function calls

    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
    åIJijæ³ķéĻ¢
    -0.08
    aper
    -0.08
    毡
    -0.07
    为åįķä½į
    -0.07
    acle
    -0.07
    åIJijä¸Ĭ级
    -0.07
    pedo
    -0.07
    æĹ¶è¡¨ç¤º
    -0.07
    å¥ł
    -0.06
    ä¸Ģ天天
    -0.06
    POSITIVE LOGITS
    еÑĤка
    0.08
    ä¸įä¹ı
    0.07
    "](
    0.07
    æģ¯
    0.07
    estra
    0.06
    çĽ
    0.06
    èijĽ
    0.06
    éch
    0.06
    schild
    0.06
    _callable
    0.06
    Activations Density 0.008%

    No Known Activations