© 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. 49841
    Prev
    Next
    INDEX
    Explanations

    gluons, color charge

    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
    ARGV
    -0.08
    £¼
    -0.08
    ç®Ķ
    -0.08
    oucher
    -0.08
    بÙĪد
    -0.08
    西æ¹ĸ
    -0.08
    ç»ıæµİæĬĢæľ¯
    -0.07
    äºŃäºŃ
    -0.07
    NECT
    -0.07
    iÄĻ
    -0.07
    POSITIVE LOGITS
    æĢĴ
    0.08
    åħ
    0.07
     Discipline
    0.07
    èī²
    0.07
    ang
    0.07
    æ·±å¤Ħ
    0.06
    ç¥Ń
    0.06
     disciplinary
    0.06
    纪å¾ĭ
    0.06
    ä¸īä¸Ń
    0.06
    Activations Density 0.012%

    No Known Activations