© 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. 62287
    Prev
    Next
    INDEX
    Explanations

    table separators

    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
     Disp
    -0.09
    rial
    -0.08
    Disp
    -0.08
    chor
    -0.07
    orial
    -0.07
    portiva
    -0.07
    ifact
    -0.07
    ful
    -0.07
    å¾Ĵ
    -0.07
    åı£æ°Ķ
    -0.07
    POSITIVE LOGITS
    scription
    0.07
    teil
    0.07
    hd
    0.07
    />\
    0.07
    æİĴçļĦ
    0.07
    大èĥľ
    0.07
    ovol
    0.07
    æĽ´æĸ°æĹ¥æľŁ
    0.07
    ampu
    0.07
    ench
    0.06
    Activations Density 0.016%

    No Known Activations