© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30056
    Prev
    Next
    INDEX
    Explanations

    muscle contracts

    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
    ä¿ĬæĿ°
    -0.08
    æĨ¨
    -0.07
    çijŀ
    -0.06
     unless
    -0.06
    aten
    -0.06
    è¿Ļ对äºİ
    -0.06
    æĹ¢åı¯
    -0.06
     pec
    -0.06
     non
    -0.06
     routing
    -0.06
    POSITIVE LOGITS
    è¶Ĭ
    0.10
    è¶ĬæĹ©
    0.10
    è¶Ĭæĺ¯
    0.09
    kiye
    0.09
    è¶Ĭé«ĺ
    0.09
    è°¢
    0.08
    ardt
    0.08
    å°±ä¼ļ导èĩ´
    0.08
    è¶Ĭéķ¿
    0.08
     коÑĢÑĢеÑģп
    0.08
    Activations Density 0.147%

    No Known Activations