© 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. 17721
    Prev
    Next
    INDEX
    Explanations

    Native, Indigenous, Aboriginal peoples

    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
    åĶ¯ç¾İ
    -0.09
    enet
    -0.09
    æ±¾
    -0.08
    æ±°
    -0.08
    æĥħ趣
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    æ¸Ń
    -0.08
    TRS
    -0.08
    涤
    -0.08
    áĢħ
    -0.08
    POSITIVE LOGITS
    æ°ijæĹı
    0.14
     Indigenous
    0.14
     Native
    0.13
     Aboriginal
    0.13
    å°ijæķ°æ°ijæĹı
    0.12
     indigenous
    0.12
    éħĭ
    0.11
    æ°ijæĹıæĸĩåĮĸ
    0.11
    ç¾Į
    0.11
    .Native
    0.10
    Activations Density 0.202%

    No Known Activations