© 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. 40756
    Prev
    Next
    INDEX
    Explanations

    (n) or (letter) followed by )

    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
    (
    -0.09
    edly
    -0.07
    æ¥Ń
    -0.07
    èºĩ
    -0.07
    ï¼Ī
    -0.07
    Ĩ
    -0.07
    کارÛĮ
    -0.07
    ÑĮе
    -0.06
    es
    -0.06
    ingly
    -0.06
    POSITIVE LOGITS
    ÑģлÑı
    0.08
    éģĹçĹĩ
    0.08
    åIJĦç§įåIJĦæł·
    0.07
    ãĤĪãģĨãģ«
    0.07
    ä¹Łæĺ¯æľĢ
    0.07
    Ñİ
    0.07
     aanwe
    0.07
    omi
    0.07
    ullet
    0.07
    uiltin
    0.07
    Activations Density 0.113%

    No Known Activations