© 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. 19900
    Prev
    Next
    INDEX
    Explanations

    let, suppose, calculate, solve

    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
    åĽĽéĢļ
    -0.07
    é¦Ĩ
    -0.07
     Sabato
    -0.07
    liz
    -0.07
    建设éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    -0.07
    åħ¨åı°
    -0.07
    icoli
    -0.07
    оÑĩе
    -0.07
     lá»iji
    -0.07
    æ½ĩ
    -0.06
    POSITIVE LOGITS
    ä¸ĢæĿ¥
    0.08
    éĿ©
    0.07
    æĺł
    0.07
    åĬ¨
    0.07
     nad
    0.07
    aven
    0.07
    家家
    0.07
    éĩĮæĺĤ
    0.06
    -dashboard
    0.06
    åĺĺ
    0.06
    Activations Density 0.206%

    No Known Activations