© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50055
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    åѦåijĺ们
    -0.09
    otime
    -0.09
    åľ¨æīĭ
    -0.09
    æĪĺ士们
    -0.08
    æķ°æ¬¡
    -0.08
    éĿĴ年人
    -0.08
    å®ĥ们
    -0.08
    åĽłä¸ºå®ĥ们
    -0.08
    è¿Ļ家ä¼Ļ
    -0.08
    éĢīæīĭ们
    -0.08
    POSITIVE LOGITS
    人æķ°
    0.14
    人æķ°çļĦ
    0.12
     who
    0.10
    人æķ¸
    0.10
    åħ¨åĵ¡
    0.10
    åIJįåįķ
    0.10
    who
    0.08
    çļĦ人æķ°
    0.08
    群ä½ĵçļĦ
    0.08
    ãģĮãģĦãĤĭ
    0.08
    Activations Density 0.031%

    No Known Activations