© 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. 41574
    Prev
    Next
    INDEX
    Explanations

    hide, clear, cutting, group, backward, stick

    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
     EITHER
    -0.09
    Either
    -0.08
     Either
    -0.08
    롬
    -0.08
    RIEND
    -0.08
    çļĦå¤ĸå½¢
    -0.08
    尾页
    -0.07
    Ùİائ
    -0.07
    æľ«é¡µ
    -0.07
    åIJĮæ¯Ķä¸Ĭåįĩ
    -0.07
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.09
    æĪĸèĢħ说
    0.08
    (?)
    0.08
     or
    0.08
     (?)
    0.08
    æĪĸ
    0.07
     maybe
    0.07
    æĪĸéĿŀ
    0.07
     (?
    0.07
    หรืà¸Ń
    0.07
    Activations Density 0.054%

    No Known Activations