© 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. 15289
    Prev
    Next
    INDEX
    Explanations

    socio-occupational function and activities

    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
    --+
    -0.07
    åįģåĽĽç«ł
    -0.07
    heads
    -0.06
    umos
    -0.06
    uah
    -0.06
     Babies
    -0.06
     tame
    -0.06
    à¸Ľà¸£à¸°à¸Ĭ
    -0.06
    ç¥Ŀç¦ıä½ł
    -0.06
     tick
    -0.06
    POSITIVE LOGITS
    /social
    0.10
    æĹ¥å¸¸çĶŁæ´»
    0.10
    社交
    0.10
     social
    0.09
    åĴĮ社ä¼ļ
    0.09
    social
    0.09
    çĶŁæ´»çļĦ
    0.09
    åĴĮçĶŁæ´»
    0.09
    çĶŁæ´»
    0.09
    .social
    0.08
    Activations Density 0.238%

    No Known Activations