© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    opportunity

    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
    ä¹ŁæľīæīĢ
    -0.10
     magari
    -0.09
     quizá
    -0.09
     ربÙħا
    -0.08
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    æľī好çļĦ
    -0.08
    åı¯èĥ½ä¼ļ导èĩ´
    -0.08
    æĻļéĹ´
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
    POSITIVE LOGITS
     math
    0.08
     appunto
    0.07
    缺ä¸Ģä¸įåı¯
    0.07
     altså
    0.07
    å°±åĥı
    0.07
    ãģĤãģı
    0.07
    å°±è¿Ļæł·
    0.06
    ä»»ä½ķåħ¶ä»ĸ
    0.06
    æķ°åѦ
    0.06
    èĤīçľ¼
    0.06
    Activations Density 0.007%

    No Known Activations