© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44214
    Prev
    Next
    INDEX
    Explanations

    okay

    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
    eves
    -0.10
    ä¹ĭä¸ĢçļĦ
    -0.10
    peon
    -0.10
    elter
    -0.09
    yard
    -0.09
    colas
    -0.09
    à¸Ĭาà¸ķิ
    -0.09
    <|box_end|>
    -0.09
    icca
    -0.09
    arco
    -0.09
    POSITIVE LOGITS
    erweise
    0.09
    ance
    0.08
    lah
    0.08
    же
    0.07
    ÑĩеÑĢед
    0.07
    åħ¶
    0.07
    ÑĢанже
    0.07
    ting
    0.07
    bserv
    0.07
    iliary
    0.06
    Activations Density 0.009%

    No Known Activations