© 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. 47727
    Prev
    Next
    INDEX
    Explanations

    describes product features

    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
    ä¸ĭä¸ĢæŃ¥
    -0.10
    æĸ¯åŁº
    -0.10
    æľīä¸Ģå®ļ
    -0.09
    å·¾
    -0.09
    hazi
    -0.09
    å¼Ħå¾Ĺ
    -0.09
    满æĢĢ
    -0.09
    æĿµ
    -0.09
    äºĨè§£æĽ´å¤ļ
    -0.09
     AMA
    -0.09
    POSITIVE LOGITS
     features
    0.10
    /features
    0.09
    ä»İä¸ļ
    0.09
    åĨħç½®
    0.08
    features
    0.08
    Features
    0.08
    侧éĿ¢
    0.08
    æł¸å¿ĥæĬĢæľ¯
    0.08
    (features
    0.08
    åIJ¬è¯¾
    0.08
    Activations Density 0.173%

    No Known Activations