© 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. 966
    Prev
    Next
    INDEX
    Explanations

    sociology and social sciences

    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
    æĸĩåĵ²
    -0.07
    æłĪ
    -0.07
     aer
    -0.07
    nable
    -0.07
    éĩĮç¨ĭ
    -0.07
    驾
    -0.07
    æµ·éģĵ
    -0.07
    éĻµ
    -0.07
     optimizations
    -0.06
     delt
    -0.06
    POSITIVE LOGITS
     sociology
    0.12
     Sociology
    0.11
    社ä¼ļåѦ
    0.11
     social
    0.10
     soci
    0.10
    æĺ¯ç¤¾ä¼ļ
    0.10
    社ä¼ļ
    0.10
    çļĦ社ä¼ļ
    0.09
     Social
    0.09
    social
    0.09
    Activations Density 0.040%

    No Known Activations