© 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. 47913
    Prev
    Next
    INDEX
    Explanations

    appearance, aesthetics, and look

    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
    åģ¥åħ¨
    -0.07
    ä½ĵä¼ļ
    -0.07
    rops
    -0.07
    éĺ®
    -0.07
    æķĻ导
    -0.07
     gist
    -0.06
    å¿«ä¹IJçļĦ
    -0.06
     exhaustive
    -0.06
     primaryKey
    -0.06
    åı¯éĿłçļĦ
    -0.06
    POSITIVE LOGITS
    ç¾İè§Ĥ
    0.15
    å¤ĸè§Ĥ
    0.14
     aesthetics
    0.13
     appearance
    0.13
    è§Ĩè§īæķĪæŀľ
    0.12
     aesthetic
    0.12
    çļĦå¤ĸè§Ĥ
    0.12
     aest
    0.12
    è§Ĩè§īä¸Ĭ
    0.11
     appeal
    0.10
    Activations Density 0.428%

    No Known Activations