© 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. 10418
    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
    éĤ£äºº
    -0.07
    è¿Ļ人
    -0.07
    éĤ£ä¸ªäºº
    -0.07
    ä¸ĢåĪĢ
    -0.07
    äºĮèĢħ
    -0.07
    åıĮ线
    -0.07
    æľ¬äººçļĦ
    -0.07
    è¿Ļ两ç§į
    -0.06
    æŃ¤äºº
    -0.06
    è¿Ļ家ä¼Ļ
    -0.06
    POSITIVE LOGITS
     collectively
    0.15
     themselves
    0.13
    éĽĨä½ĵ
    0.12
     collective
    0.12
    个个
    0.12
     közül
    0.11
    æĺ¯ä¸Ģ群
    0.11
    æıĥ
    0.11
    ç»ĦæĪIJçļĦ
    0.11
    ç»ĦæĪIJ
    0.11
    Activations Density 0.607%

    No Known Activations