© 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. 16941
    Prev
    Next
    INDEX
    Explanations

    cell carcinoma

    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
    åįĬå¹´çļĦ
    -0.07
    éĹ´æİ¥
    -0.06
    两个
    -0.06
    ä¸įç»ı
    -0.06
     '/
    -0.06
    两次
    -0.06
    ucci
    -0.06
     Sop
    -0.06
    stat
    -0.06
    oad
    -0.06
    POSITIVE LOGITS
     varying
    0.13
    ä¸įåIJĮç¨ĭ度
    0.13
    ä¸įåIJĮç¨ĭ度çļĦ
    0.13
    vary
    0.11
     ÑĢазлиÑĩной
    0.10
     vary
    0.10
     ваÑĢÑĮи
    0.10
     varied
    0.10
     varies
    0.10
     ÑĢазной
    0.10
    Activations Density 0.206%

    No Known Activations