© 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. 39636
    Prev
    Next
    INDEX
    Explanations

    parts of a series or work

    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
    ä»»ä½ķä¸Ģç§į
    -0.08
    æĸ°ä¹¦æݨèįIJ
    -0.07
    Values
    -0.07
    è°ļè¯Ń
    -0.07
    ä¸Ĭä¸ĢæĿ¡
    -0.07
    ä¸Ģç§Ĵ
    -0.07
    áĥ£áĥļáĥĺ
    -0.07
    iani
    -0.07
    -values
    -0.06
    äºĮåįĥ
    -0.06
    POSITIVE LOGITS
     chapters
    0.13
     sections
    0.12
     section
    0.11
     thematic
    0.10
    _sections
    0.10
    ç«łèĬĤ
    0.09
     subsection
    0.09
     chapter
    0.09
     numbered
    0.09
    _modules
    0.09
    Activations Density 0.484%

    No Known Activations