© 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. 10169
    Prev
    Next
    INDEX
    Explanations

    newspapers and publications

    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
    丰满
    -0.10
    å·¥ä½ľç«Ļ
    -0.10
    åĬŀåħ¬æ¥¼
    -0.09
    æĶ¾æĿ¾
    -0.09
    ç»Ī
    -0.09
    åĬ¨çī©åĽŃ
    -0.09
    èĩªçĦ¶èĢĮ
    -0.09
     занÑıÑĤ
    -0.09
    åħ»æ®ĸåľº
    -0.09
    仪å¼ı
    -0.09
    POSITIVE LOGITS
     Times
    0.10
    æĿĤå¿Ĺ
    0.10
     Magazine
    0.10
    æŶæĬ¥
    0.10
     news
    0.09
    ä¼łæĿ¥
    0.09
    æĹ¥æĬ¥éģĵ
    0.09
     Journal
    0.09
    æĸ°éĹ»ç½ij
    0.09
     tạp
    0.09
    Activations Density 0.162%

    No Known Activations