© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60011
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or specific technical terms

    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
    Negative Logits
    icient
    -0.09
     '::
    -0.08
    epam
    -0.08
    ierzch
    -0.08
    endorf
    -0.08
    itante
    -0.08
    &r
    -0.07
    éĢļ常æĥħåĨµä¸ĭ
    -0.07
    éħįç½®æĸ¹éĿ¢
    -0.07
    åįĥåįĥ
    -0.07
    POSITIVE LOGITS
    fty
    0.08
    orse
    0.07
    o
    0.07
    ĩ
    0.07
    inds
    0.07
    Ĥ
    0.06
    辨
    0.06
    ãģ¾ãģ¾
    0.06
    éĹ´çļĦ
    0.06
    fois
    0.06
    Activations Density 0.001%

    No Known Activations