© 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. 38326
    Prev
    Next
    INDEX
    Explanations

    tile and mosaic patterns

    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
    ãģ¾ãģ¾
    -0.08
    ä½ķåľ¨
    -0.08
    ¸
    -0.08
    ัà¸į
    -0.07
     opdr
    -0.07
    impin
    -0.07
     Фло
    -0.07
    ä¸įæĺİçļĦ
    -0.07
    åı¯éļıæŶ
    -0.07
     Pistol
    -0.07
    POSITIVE LOGITS
    ç¼ĿéļĻ
    0.08
    åĽ¾æ¡Ī
    0.08
    æĭ¼æİ¥
    0.08
     TILE
    0.08
    رخ
    0.07
    agle
    0.07
    igsaw
    0.07
    çłĮ
    0.07
    -pattern
    0.07
     tiles
    0.07
    Activations Density 0.016%

    No Known Activations