© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1438
    Prev
    Next
    INDEX
    Explanations

    Asian American or Canadian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sons
    -0.09
    èĭĭ
    -0.09
    ä¼ļåijĺ
    -0.09
    æĹºçĽĽ
    -0.09
    é¦ĭ
    -0.09
    lesen
    -0.09
     extremes
    -0.08
    ductive
    -0.08
    活泼
    -0.08
    atively
    -0.08
    POSITIVE LOGITS
    -Pacific
    0.13
    /ion
    0.10
    ç¿ķ
    0.10
    åŃIJéĩĮ
    0.09
    LEE
    0.09
    Appear
    0.09
    èĢĥåľº
    0.09
     countries
    0.09
    æĽ´èĥ½
    0.09
    çĨĻ
    0.09
    Activations Density 0.021%

    No Known Activations