© 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. 1636
    Prev
    Next
    INDEX
    Explanations

    free, atoroidal, definition, approximate, groups

    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
    æ°¸è¿ľæĺ¯
    -0.08
    ç§ķ
    -0.07
    åį³
    -0.07
    жнÑı
    -0.07
    åį³ä»¥
    -0.07
      ↵    ↵
    -0.07
    åĩ¡äºĭ
    -0.07
    æ¯ıä¸Ģ天
    -0.07
    angk
    -0.07
    /books
    -0.07
    POSITIVE LOGITS
    大èĩ´
    0.09
     somehow
    0.09
    大æ¦Ĥ
    0.09
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.09
     approximate
    0.08
     roughly
    0.08
    ä¸įä¸Ģå®ļ
    0.08
    -ish
    0.08
    æŁIJç§į
    0.08
     somewhat
    0.08
    Activations Density 0.061%

    No Known Activations