© 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. 29053
    Prev
    Next
    INDEX
    Explanations

    acronyms for organizations and technical terms

    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
    uesa
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    æĪijä¸Ģ个
    -0.08
    仪åĻ¨æľīéĻIJåħ¬åı¸
    -0.07
    soever
    -0.07
    åĽ½éĻħè´¸æĺĵæľīéĻIJåħ¬åı¸
    -0.07
    itzer
    -0.07
    ç»İ
    -0.07
    .iOS
    -0.07
    rooms
    -0.07
    POSITIVE LOGITS
    perial
    0.12
    ividual
    0.10
    entif
    0.10
    gnore
    0.10
    manuel
    0.09
    onesia
    0.09
    rvine
    0.09
    repid
    0.09
    ustrial
    0.09
    mediate
    0.08
    Activations Density 1.414%

    No Known Activations