© 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. 51820
    Prev
    Next
    INDEX
    Explanations

    attire and outfits

    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
    æŀķ头
    -0.07
     punch
    -0.06
    arith
    -0.06
     mouths
    -0.06
    æİ°
    -0.06
    èĦ¾æ°Ķ
    -0.06
    ç¢ij
    -0.06
    å¼Ģè¾Ł
    -0.06
     embedded
    -0.06
    çļĦæīĭæ³ķ
    -0.06
    POSITIVE LOGITS
     attire
    0.12
     worn
    0.11
    åħ¨å¥Ĺ
    0.11
    è£ħæī®
    0.11
    å¥Ĺè£ħ
    0.11
     costume
    0.10
     outfit
    0.10
    ç©¿æĪ´
    0.10
    æīĵæī®
    0.10
    两å¥Ĺ
    0.10
    Activations Density 0.259%

    No Known Activations