© 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. 3858
    Prev
    Next
    INDEX
    Explanations

    ranking calculated, order, higher

    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
    odore
    -0.11
    bies
    -0.10
    izable
    -0.09
    zinha
    -0.09
    /from
    -0.09
    ../
    -0.09
    avanaugh
    -0.09
    rlen
    -0.09
    ary
    -0.08
    orce
    -0.08
    POSITIVE LOGITS
    次çļĦ
    0.08
    furter
    0.08
    aroo
    0.08
    pole
    0.08
    o
    0.07
    eves
    0.07
    less
    0.07
    ayat
    0.07
    i
    0.07
    ush
    0.07
    Activations Density 0.016%

    No Known Activations