© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36891
    Prev
    Next
    INDEX
    Explanations

    police departments, science departments, newsrooms

    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
    æĺ¯ä¸Ģ件
    -0.09
    iel
    -0.09
    èµģ
    -0.09
    åıł
    -0.09
    æ¯Ķäºļ
    -0.08
    ä¸įåħĭä¸įåıĬ
    -0.08
    临æŶ
    -0.08
     Yap
    -0.08
    æĺ¯ä¸ĢåIJį
    -0.08
    æĸĩ书
    -0.08
    POSITIVE LOGITS
    纷纷
    0.11
    éģįå¸ĥ
    0.10
    æĻ®éģįåŃĺåľ¨
    0.09
    åIJĦèĩªçļĦ
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
     everywhere
    0.09
    åħ¨ä¸ĸçķĮ
    0.09
     worldwide
    0.09
    åIJĦèĩª
    0.09
    åŁİå¸ĤçļĦ
    0.09
    Activations Density 0.201%

    No Known Activations