© 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. 15446
    Prev
    Next
    INDEX
    Explanations

    book classifications and editions

    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
    annis
    -0.07
    itial
    -0.06
    _some
    -0.06
     vs
    -0.06
     некоÑĤоÑĢ
    -0.06
     exemple
    -0.06
    ä¸į注æĦı
    -0.06
     duplicate
    -0.06
    ç¬ĶèĢħ
    -0.06
     Whatsapp
    -0.06
    POSITIVE LOGITS
    æľ¬æĽ¸
    0.12
     isbn
    0.11
     Paperback
    0.10
     bestselling
    0.10
    isbn
    0.10
     eBook
    0.10
     Hardcover
    0.10
    æľ¬ä¹¦
    0.09
    à¹Ģลà¹Īม
    0.09
     ebook
    0.09
    Activations Density 1.277%

    No Known Activations