© 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. 17291
    Prev
    Next
    INDEX
    Explanations

    /proc/self/fd/

    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»ĬæĹ¥çļĦ
    -0.07
    loch
    -0.06
    obb
    -0.06
    allar
    -0.06
    åı¯æĺ¯ä»ĸ
    -0.06
    éĢĻåĢĭæĻĤåĢĻ
    -0.06
    но
    -0.06
    çĤķ
    -0.06
    ÑģÑĤÑĢе
    -0.06
    äºĭ
    -0.06
    POSITIVE LOGITS
    ÏħÏĩ
    0.08
    ãģ¾ãģĦ
    0.07
    LEASE
    0.07
    å¸ģ
    0.07
    å¹£
    0.07
    对ä¸Ĭè¿°
    0.07
    åı²ä¸ĬæľĢ
    0.07
    reature
    0.07
    oleh
    0.07
    åľ¨ä¸Ĭè¿°
    0.07
    Activations Density 0.064%

    No Known Activations