© 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. 56696
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    奴
    -0.07
    nisse
    -0.07
    åľ¨æīĢ
    -0.06
    ä»ĸ人
    -0.06
     أد
    -0.06
    å¾Ĺèµ·
    -0.06
    鬼
    -0.06
    ä¸īå¹´
    -0.06
     Natur
    -0.06
    çĽĸä¸ĸ
    -0.05
    POSITIVE LOGITS
    asiat
    0.08
    饮èĮ¶
    0.08
     turno
    0.08
    æĺ¯æŶåĢĻ
    0.07
    autoload
    0.07
    ä¸Ģ个女人
    0.07
    रà¥įस
    0.07
    ç±³èĬ±
    0.07
    èĮ¶æĿ¯
    0.07
    нг
    0.07
    Activations Density 0.006%

    No Known Activations