© 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. 51402
    Prev
    Next
    INDEX
    Explanations

    acupuncture channels

    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
    imba
    -0.08
    каз
    -0.07
    å¤ļ大
    -0.07
     replacements
    -0.07
    榨
    -0.07
    ä¸ī项
    -0.07
    atel
    -0.07
    游åĪĥ
    -0.07
     cores
    -0.07
     Stall
    -0.06
    POSITIVE LOGITS
    è¿ŀæİ¥
    0.09
    -connect
    0.08
     connection
    0.08
    循
    0.08
    è¿ĻæĿ¡
    0.08
    è¿ŀæİ¥åĪ°
    0.08
    connection
    0.08
    éĢĻæ¢Ŀ
    0.08
    è¿ŀæİ¥çļĦ
    0.07
     ascending
    0.07
    Activations Density 0.003%

    No Known Activations