© 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. 29908
    Prev
    Next
    INDEX
    Explanations

    chemical identifiers

    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
    arent
    -0.07
     (
    -0.07
    å°ļ书
    -0.06
    -0.06
    è¿IJåĬ¨ä¼ļ
    -0.06
    /misc
    -0.06
     by
    -0.06
    è¿ŀåIJĮ
    -0.06
     A
    -0.06
    äºĮæĺ¯
    -0.05
    POSITIVE LOGITS
    ëģĶ
    0.09
    à¸Ļิà¹īว
    0.08
    .Loader
    0.08
     manus
    0.08
    ÑıÑĤи
    0.07
     willen
    0.07
    ilig
    0.07
    çļĻ
    0.07
    ä¸İæľ¬ç«Ļ
    0.07
    поÑĤÑĢе
    0.07
    Activations Density 0.064%

    No Known Activations