© 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. 59371
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸įä¿¡
    -0.09
    udi
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
     Disqus
    -0.09
    踵
    -0.09
     бÑĥкв
    -0.08
    æĴŃç§į
    -0.08
    å¿ĥ
    -0.08
    å¿ĥæĦı
    -0.08
    å¿ĥä¸Ń
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢéĿ¢
    0.10
     Beverage
    0.09
    ä¸ĬéĻIJ
    0.09
    æĸ°å¾ģç¨ĭ
    0.08
    æ±¾
    0.08
    åIJĬ
    0.08
    âĪ¬
    0.08
    æľī趣çļĦ
    0.08
    ä¾ĭè¡Į
    0.08
     unf
    0.08
    Activations Density 0.000%

    No Known Activations