© 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. 44189
    Prev
    Next
    INDEX
    Explanations

    activity, value, points, cap, potential, reach, dispersion

    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
    skal
    -0.08
    owitz
    -0.08
    eke
    -0.08
    áĥłáĥĿ
    -0.07
    eenth
    -0.07
    aight
    -0.07
    empa
    -0.07
    åĴĮçłĶ究
    -0.07
    å©ķ
    -0.07
    alled
    -0.07
    POSITIVE LOGITS
    ستÙĩ
    0.08
    .nasa
    0.07
    éĢ¼äºº
    0.07
    å®ĪæģĴ
    0.07
    Ĩµ
    0.07
    ÙĪرد
    0.07
    ì²Ļ
    0.07
    è´¯
    0.07
     deficit
    0.07
    Ĩ
    0.07
    Activations Density 0.004%

    No Known Activations