© 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. 26285
    Prev
    Next
    INDEX
    Explanations

    Taylor & Francis / Springer Publishers

    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
    kst
    -0.09
    åĽ¢çļĦ
    -0.09
    erschaft
    -0.08
    ftime
    -0.08
    iloc
    -0.08
    åѦéĻ¢éĻ¢éķ¿
    -0.08
    é¡¹çĽ®å¼Ģåıij
    -0.08
     Devin
    -0.08
    (Output
    -0.08
    chure
    -0.08
    POSITIVE LOGITS
    æĹĹä¸ĭçļĦ
    0.07
     via
    0.06
    /
    0.06
    ore
    0.06
    æ·«
    0.06
    bj
    0.06
     Publishing
    0.06
    via
    0.06
    课åīį
    0.06
    x
    0.06
    Activations Density 0.017%

    No Known Activations