© 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. 58000
    Prev
    Next
    INDEX
    Explanations

    fine particles, powder, art, light, sport

    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
    åĴĮåIJĮäºĭ
    -0.09
    .joda
    -0.09
    xico
    -0.08
    ãĤ¤ãĥĦ
    -0.08
    ÛĮزÛĮ
    -0.08
    иÑĢов
    -0.08
    ustr
    -0.08
    зино
    -0.08
    szy
    -0.08
    folios
    -0.08
    POSITIVE LOGITS
    (xi
    0.09
    plorer
    0.09
    ele
    0.08
    urtle
    0.08
    eben
    0.08
    ek
    0.08
    idler
    0.07
    COPE
    0.07
    ea
    0.07
    atics
    0.07
    Activations Density 0.013%

    No Known Activations