© 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. 27182
    Prev
    Next
    INDEX
    Explanations

    chemical groups like tBu, Cy

    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
     conjunta
    -0.07
    stad
    -0.07
    ulk
    -0.07
    åħŃ级
    -0.07
    寥寥
    -0.06
    usen
    -0.06
     Ey
    -0.06
     havoc
    -0.06
    anit
    -0.06
    oday
    -0.06
    POSITIVE LOGITS
    Resize
    0.07
    西çľģ
    0.07
    PathParam
    0.07
     Agen
    0.07
    ión
    0.07
    稿件æĿ¥æºIJ
    0.07
     weighing
    0.07
    车ç¨ĭ
    0.07
    ias
    0.07
    edith
    0.07
    Activations Density 0.004%

    No Known Activations