© 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. 49122
    Prev
    Next
    INDEX
    Explanations

    elements, aroma, ingredients

    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
    geries
    -0.08
    å¤ļåģļ
    -0.07
    æĿ¥åĩ½
    -0.07
    chern
    -0.07
    ç»ĻæĪijä¸Ģ个
    -0.07
    æķĻ书
    -0.07
    ëĭ¨ì²´
    -0.07
    imon
    -0.07
    åħ±åĴĮåĽ½
    -0.07
    æĻ´å¤©
    -0.06
    POSITIVE LOGITS
    åħĥåĻ¨ä»¶
    0.08
    åħĥ件
    0.07
    ä¸Ģä¼Ĺ
    0.07
    åħ¨éĥ¨
    0.07
    é£ŁæĿIJ
    0.07
     Ingredients
    0.07
     elements
    0.07
    å°ĨæīĢæľī
    0.07
    _symbols
    0.07
    鼶件
    0.07
    Activations Density 0.569%

    No Known Activations