© 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. 20018
    Prev
    Next
    INDEX
    Explanations

    mayor, spooks, prizes, advocate

    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
     (
    -0.07
    Âł
    -0.07
    æĪĸèĢħ说
    -0.06
    uruan
    -0.06
    abbrev
    -0.06
    æij©
    -0.06
     either
    -0.06
    ili
    -0.06
    åĩī
    -0.06
    åĴ¬çīĻ
    -0.06
    POSITIVE LOGITS
    çŀij
    0.08
     nantinya
    0.07
    ضÙĬ
    0.07
    èĥ½åĬĽåĪĨæŀIJ
    0.07
    enner
    0.07
    æĹ¥ä¸Ĭ
    0.07
    ä¸Ĭä¸ĢæĿ¡
    0.07
    åĮĸåıijå±ķ
    0.07
    vn
    0.07
    \Config
    0.07
    Activations Density 0.015%

    No Known Activations