© 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. 31308
    Prev
    Next
    INDEX
    Explanations

    the followed by a 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
    è¿Ļæĺ¯åĽłä¸º
    -0.08
    PrototypeOf
    -0.08
    ippi
    -0.08
    سÙĬØ©
    -0.07
    çļĦ大éĩı
    -0.07
    âĢ¦]
    -0.07
     ведÑĮ
    -0.07
    éĬĺ
    -0.07
    icz
    -0.07
    çıĬçıĬ
    -0.07
    POSITIVE LOGITS
    æĹłè®ºä»İ
    0.07
    æĸ°åĬłåĿ¡
    0.07
     overall
    0.07
    æķ´ä¸ªéĹ®é¢ĺ
    0.07
     Ñģмело
    0.07
    æķ´ä¸ª
    0.06
    ä¹ĭ为
    0.06
    ldb
    0.06
    éĹ®é¢ĺæĿ¥äºĨ
    0.06
     ÑģледÑĥÑİÑīим
    0.06
    Activations Density 0.038%

    No Known Activations