© 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. 43599
    Prev
    Next
    INDEX
    Explanations

    function with 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
    OMP
    -0.07
    éļĪ
    -0.07
    ä¸įåĩı
    -0.06
    OK
    -0.06
    вÑĸв
    -0.06
    以åĨħ
    -0.06
    attr
    -0.06
    éĩijåŃĹå¡Ķ
    -0.06
     Pyramid
    -0.06
    æ±ĩ
    -0.06
    POSITIVE LOGITS
    沧
    0.07
    ertz
    0.07
    人æ°ijåħ±åĴĮåĽ½
    0.07
    æ´±
    0.07
    élé
    0.07
    erval
    0.07
    wez
    0.07
    æ¶Īéĺ²è®¾æĸ½
    0.07
    å¹¹
    0.07
    uruhan
    0.07
    Activations Density 0.001%

    No Known Activations