© 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. 24186
    Prev
    Next
    INDEX
    Explanations

    ultrasound-based sensors

    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
    ç»İ
    -0.08
     Ballard
    -0.07
    èĴĤæĸ¯
    -0.07
    ĮĢ
    -0.07
    çİ¥
    -0.07
     industry
    -0.07
    è·Į
    -0.07
    æľºä¼ļ
    -0.07
     bais
    -0.06
    缴æİ¥æĪĸ
    -0.06
    POSITIVE LOGITS
    езде
    0.07
    compatible
    0.07
     Det
    0.07
    stown
    0.06
    ope
    0.06
    strup
    0.06
    proto
    0.06
    itz
    0.06
    elder
    0.06
    èĩīèī²
    0.06
    Activations Density 0.003%

    No Known Activations