© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29602
    Prev
    Next
    INDEX
    Explanations

    punctuations followed by word

    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
    Negative Logits
    éĥ½æĥ³
    -0.11
    è¯ł
    -0.09
    åľ¨å¤ĸéĿ¢
    -0.09
    èįĨ
    -0.09
    é©®
    -0.08
    åľ¨æĹ¥æľ¬
    -0.08
    æľ¬èº«å°±æĺ¯
    -0.08
    çĶŁåŃĺ
    -0.08
    涸
    -0.08
    çĮ´
    -0.08
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.13
    æİ¥çĿĢ
    0.12
    èĢĮåIJİ
    0.11
    éļıåIJİ
    0.10
    ä¹ĭåIJİ
    0.10
    æİ¥èijĹ
    0.10
    ä¹ĭå¾Į
    0.09
     followed
    0.09
    åIJİçļĦ
    0.09
     заÑĤем
    0.09
    Activations Density 0.150%

    No Known Activations