© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    genetic ancestry and population 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
    è¿Ļ家ä¼Ļ
    -0.09
    åĬ¨éĿĻ
    -0.08
    é¤Į
    -0.08
    饵
    -0.08
     verbs
    -0.07
    occo
    -0.07
    éĽĨ
    -0.07
    å¾Ģ常
    -0.07
    zzo
    -0.07
    issan
    -0.07
    POSITIVE LOGITS
     ancestry
    0.14
     ancest
    0.11
     genetic
    0.11
     ancestral
    0.11
    人群ä¸Ń
    0.10
     population
    0.10
     ethnic
    0.10
     populations
    0.10
    人åı£çļĦ
    0.10
    population
    0.09
    Activations Density 0.091%

    No Known Activations