© 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. 49371
    Prev
    Next
    INDEX
    Explanations

    code examples, lists, numbers

    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
    .tim
    -0.06
    轩è¾ķ
    -0.06
    ä½µ
    -0.06
    Nov
    -0.06
    çļĦèĩªçĶ±
    -0.06
    chsel
    -0.06
    regular
    -0.06
    é¾Ļ骨
    -0.06
     S
    -0.06
    полÑĮ
    -0.06
    POSITIVE LOGITS
    表达æĸ¹å¼ı
    0.08
    表达
    0.08
    tui
    0.08
    åı¥åŃIJ
    0.08
    ebo
    0.08
    obox
    0.07
     description
    0.07
    ipel
    0.07
    ept
    0.07
    åIJİéĿ¢çļĦ
    0.07
    Activations Density 0.025%

    No Known Activations