© 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. 39982
    Prev
    Next
    INDEX
    Explanations

    zero followed by 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
    enhagen
    -0.08
    Assignable
    -0.07
    gence
    -0.06
    ategorized
    -0.06
    è·µè¸ı
    -0.06
    گذارÛĮ
    -0.06
    astic
    -0.06
    Ĥ¬
    -0.06
    Ĵáŀ
    -0.06
    åīįçļĦ
    -0.06
    POSITIVE LOGITS
    Ñīем
    0.08
    rof
    0.08
    /OR
    0.08
    able
    0.08
    rette
    0.07
    ehl
    0.07
    inata
    0.07
    .GetLength
    0.07
    ables
    0.07
    ABLE
    0.07
    Activations Density 0.013%

    No Known Activations