© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44256
    Prev
    Next
    INDEX
    Explanations

    set theory notation

    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
    Negative Logits
    adio
    -0.07
    INLINE
    -0.07
    ÙĨدÙĩ
    -0.07
    idge
    -0.07
    ignan
    -0.07
    ç¦
    -0.06
    æĿ¿å¼ı
    -0.06
    opoulos
    -0.06
    éĩį大éĹ®é¢ĺ
    -0.06
    onar
    -0.06
    POSITIVE LOGITS
     subset
    0.14
    subset
    0.12
     consisted
    0.11
     consists
    0.11
    éĽĨåIJĪ
    0.10
     subsets
    0.10
     Subset
    0.10
    交éĽĨ
    0.10
    =set
    0.10
    åIJįåįķ
    0.10
    Activations Density 0.034%

    No Known Activations