© 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. 42252
    Prev
    Next
    INDEX
    Explanations

    initializations, domain, last, belongs

    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
    举ä¸ĸ
    -0.08
    eme
    -0.07
    人å¿ĥ
    -0.07
    é«ĺ峰论åĿĽ
    -0.07
    emy
    -0.07
    omu
    -0.07
    rial
    -0.07
    theses
    -0.07
    æ®ĥ
    -0.07
    eten
    -0.07
    POSITIVE LOGITS
    illant
    0.07
    èĩª
    0.07
    æĪij为群ä¼ĹåĬŀå®ŀäºĭ
    0.06
     ÙĦÙĦØ·
    0.06
    èĢĮåIJİ
    0.06
    馨
    0.06
    rosse
    0.06
    uide
    0.06
    æħ
    0.06
    éķ
    0.06
    Activations Density 0.317%

    No Known Activations