© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23030
    Prev
    Next
    INDEX
    Explanations

    response.url or items.map

    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
    çļĦ人æĿ¥è¯´
    -0.08
     ...)
    -0.08
    ï¼īãĢį
    -0.08
    acent
    -0.08
    æĢİ麽
    -0.08
    )”
    -0.08
    âĢ¦”
    -0.07
    )="
    -0.07
    åĪĻåı¯
    -0.07
    agger
    -0.07
    POSITIVE LOGITS
    å·įå·į
    0.07
    gba
    0.07
     cast
    0.07
     **.**
    0.06
    !(
    0.06
    plo
    0.06
    ãĢĤï¼Ī
    0.06
    æľĿ
    0.06
    oooooooo
    0.06
    .!
    0.06
    Activations Density 0.167%

    No Known Activations