© 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. 7934
    Prev
    Next
    INDEX
    Explanations

    working, less, recommend, successful, hits

    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
    erot
    -0.07
    åľ¨è¿ĻäºĽ
    -0.07
     ëĮĢìĭł
    -0.07
    åIJİç»ı
    -0.07
    éĢļéĢļ
    -0.06
    ubin
    -0.06
    æľ¬ç«ĻåĨħ容
    -0.06
    åĪ°æѤ
    -0.06
    屡屡
    -0.06
    endant
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.08
     ÑĤоже
    0.07
    åĴĮ第
    0.07
    metic
    0.07
    ürg
    0.07
    веÑĤа
    0.07
    chs
    0.07
    ãģ¨ãģĦãģ£ãģ¦
    0.07
    ono
    0.07
    åĴĮ第äºĮ
    0.07
    Activations Density 0.062%

    No Known Activations