© 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. 43187
    Prev
    Next
    INDEX
    Explanations

    news highlights

    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
    åģıåģı
    -0.08
    áĥ®áĥĿ
    -0.07
    ehler
    -0.07
     ÐŁÐ¾Ð¿ÑĢо
    -0.07
    èĿĩ
    -0.07
    inker
    -0.07
    erien
    -0.07
    çĻĸ
    -0.07
    eller
    -0.07
    crease
    -0.06
    POSITIVE LOGITS
    unti
    0.08
    ãĥĿãĤ¤ãĥ³ãĥĪãģ¯
    0.07
    uml
    0.07
    [#
    0.07
    CellValue
    0.07
    atar
    0.07
     domicili
    0.06
    ago
    0.06
    ANI
    0.06
    лаÑĤ
    0.06
    Activations Density 0.002%

    No Known Activations