© 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. 46348
    Prev
    Next
    INDEX
    Explanations

    this + noun

    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
    ãģ¾ãĤĵ
    -0.07
    رÛĮاÙĨ
    -0.06
    mena
    -0.06
     Schul
    -0.06
    Ñīенко
    -0.06
    éĤ£ä¸ªæŶåĢĻ
    -0.06
    è§Ĥ念åĴĮ
    -0.06
    éĢ®
    -0.06
    äºİä¸Ģ
    -0.06
    æĿ¥å¾Ĺ
    -0.06
    POSITIVE LOGITS
    à¤łà¤¾
    0.08
    verka
    0.08
    áŁĭ
    0.08
    çļĦ好åıĭ
    0.08
    undra
    0.07
    æĹ¥åĪ¶
    0.07
    fen
    0.07
    ä»»æĢ¨
    0.07
    åĪĽä¼ĺ
    0.07
     vej
    0.07
    Activations Density 0.007%

    No Known Activations