© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    fashion trends and designers

    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
    æĸĩç¬Ķ
    -0.07
    åħ¨åĬĽ
    -0.06
    å¯Ł
    -0.06
    çIJ´
    -0.06
     operation
    -0.06
    åĸĦ
    -0.06
    éĻį
    -0.06
     ÑĢезÑĮ
    -0.05
    æĸĩéĩĩ
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    åįķåĵģ
    0.11
    çīĪåŀĭ
    0.11
    çĻ¾æIJŃ
    0.11
     styles
    0.11
     designers
    0.10
    款å¼ı
    0.10
     Vogue
    0.10
    å¤įåı¤
    0.10
     designer
    0.10
    å»ĵ
    0.10
    Activations Density 0.388%

    No Known Activations