© 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. 2042
    Prev
    Next
    INDEX
    Explanations

    every topic

    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
    æģIJ
    -0.06
     temper
    -0.06
    _reference
    -0.06
     supposed
    -0.06
     conject
    -0.06
    atos
    -0.06
    åı½
    -0.06
    ä¼Ĭ丽èİİçĻ½
    -0.06
    Relative
    -0.06
    ç»Ŀ对ä¸įä¼ļ
    -0.06
    POSITIVE LOGITS
    åı¯è¡ĮçļĦ
    0.08
    交éĽĨ
    0.08
    满足
    0.08
    åı¯è¡ĮæĢ§
    0.08
    为满足
    0.08
    åij½ä¸Ń
    0.08
    èĸª
    0.08
    åIJĮæŶè¿ĺè¦ģ
    0.08
     feasible
    0.08
    符åIJĪæĿ¡ä»¶çļĦ
    0.08
    Activations Density 0.001%

    No Known Activations