© 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. 10813
    Prev
    Next
    INDEX
    Explanations

    order.all or order of

    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
    wins
    -0.08
    eties
    -0.07
    templ
    -0.07
    setzung
    -0.07
     Kompet
    -0.07
    ä¸Ģ覧
    -0.07
    fér
    -0.06
    å·²æĺ¯
    -0.06
    FER
    -0.06
    çļĦäºĨ解
    -0.06
    POSITIVE LOGITS
    stech
    0.07
    åĬ¨äººçļĦ
    0.07
    èĩªå·±è¢«
    0.07
    人被
    0.06
    æŶæīĢ
    0.06
    ูà¸ģ
    0.06
    ä¿Ĺ
    0.06
    æ´»åĬ¨åľ¨
    0.06
    æĤī
    0.06
    对éĤ£äºĽ
    0.06
    Activations Density 0.075%

    No Known Activations