© 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. 43620
    Prev
    Next
    INDEX
    Explanations

    ethnic and minority groups

    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
    inesis
    -0.07
    enna
    -0.06
    olina
    -0.06
    åĩ¡äºº
    -0.06
     stationary
    -0.06
    åĽłæĿIJ
    -0.06
    iom
    -0.06
    ä¸ĵäººè´Łè´£
    -0.06
    å¿ĹæĪIJ
    -0.06
    æľīæĪIJæķĪ
    -0.06
    POSITIVE LOGITS
     minority
    0.11
     outnumber
    0.11
     minorities
    0.11
     majority
    0.11
     ethnic
    0.11
     ethnicity
    0.11
     ethn
    0.10
    ethnic
    0.10
    èģļå±ħ
    0.10
     пÑĢожив
    0.10
    Activations Density 0.222%

    No Known Activations