© 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. 13027
    Prev
    Next
    INDEX
    Explanations

    trends and fashion

    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
    ķĮ
    -0.08
    éģĩåĪ°åĽ°éļ¾
    -0.08
    URNS
    -0.08
    æŶèĩ³ä»Ĭ
    -0.08
    amet
    -0.07
    è¿Ħä»Ĭ
    -0.07
     backstory
    -0.07
     Sud
    -0.07
    使åĩº
    -0.07
    åĪ«æľī
    -0.07
    POSITIVE LOGITS
     trends
    0.17
     trend
    0.13
    æĽ´æĸ°
    0.13
     Trends
    0.13
    è¶ĭåĬ¿
    0.13
     updates
    0.13
    æľĢæĸ°
    0.13
    åĬ¨åIJij
    0.13
    æĽ´æĸ°çļĦ
    0.13
    trend
    0.12
    Activations Density 0.263%

    No Known Activations