© 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. 48903
    Prev
    Next
    INDEX
    Explanations

    Japanese province, warriors, tea

    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
    \CMS
    -0.10
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    serrat
    -0.09
    è¦ģåģļ
    -0.09
    翱
    -0.09
    Ulus
    -0.09
     tü
    -0.09
    .Lib
    -0.09
     statusCode
    -0.09
     Stir
    -0.09
    POSITIVE LOGITS
    åľ¨æĹ¥æľ¬
    0.14
    æĹ¥æľ¬ãģ®
    0.12
    æĹ¥æľ¬
    0.11
     Japanese
    0.10
    ä¸ĸ家
    0.10
    æĹ¥æľ¬äºº
    0.10
    åĩij
    0.09
    书éĻ¢
    0.09
    çĽĤ
    0.09
    Ñģан
    0.09
    Activations Density 0.132%

    No Known Activations