© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50941
    Prev
    Next
    INDEX
    Explanations

    founder of industries

    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
    aut
    -0.09
    пÑĢов
    -0.09
    çĶ¨å·¥
    -0.09
    ç¹ģ
    -0.09
    ringe
    -0.09
    跨度
    -0.08
    ä»ĸå°±
    -0.08
    æĭį
    -0.08
    åĽ¤
    -0.08
    uated
    -0.08
    POSITIVE LOGITS
    æľ¬ç½ijç«Ļ
    0.09
     squir
    0.09
    æĸ°æĬĢæľ¯
    0.09
    æīĢæıIJä¾Ľ
    0.08
     reb
    0.08
    von
    0.08
    çļĦå¿ĥæĢģ
    0.08
    æ´İ
    0.08
    èĩªæĿ¥
    0.08
     sew
    0.08
    Activations Density 0.109%

    No Known Activations