© 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. 24291
    Prev
    Next
    INDEX
    Explanations

    complex exponential functions like $e^{ix^2}$ or $e^{-x^2}$

    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
    ÑģлÑı
    -0.07
    Ñģлей
    -0.07
    olini
    -0.06
    zelfde
    -0.06
    ordat
    -0.06
    以ä¸ĬçļĦ
    -0.06
    ç¼¥ç¼Ī
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    éªı
    -0.06
    ories
    -0.06
    POSITIVE LOGITS
    leanor
    0.08
    incr
    0.07
    menta
    0.07
    andu
    0.07
    agnol
    0.07
    aminer
    0.07
    locs
    0.07
    igna
    0.07
    人å±ħ
    0.07
    linky
    0.07
    Activations Density 0.002%

    No Known Activations