© 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. 10270
    Prev
    Next
    INDEX
    Explanations

    derivative or integral formulas

    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
    foon
    -0.08
    æĺİçģ¯
    -0.06
    umo
    -0.06
    uto
    -0.06
    è´¢éĻ©
    -0.06
    ture
    -0.06
    游走
    -0.06
    ä¸ŃåĽ½åĽ½éĻħ
    -0.06
    ute
    -0.06
    rut
    -0.06
    POSITIVE LOGITS
    次äºİ
    0.08
    ضة
    0.08
    å·¥ç¨ĭçŃī
    0.08
    Įĵ
    0.07
    ---</
    0.07
    ç´
    0.07
    æĺ¯æĪij们çļĦ
    0.07
    RAR
    0.07
    hood
    0.07
    itesse
    0.07
    Activations Density 0.004%

    No Known Activations