© 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. 12417
    Prev
    Next
    INDEX
    Explanations

    clothing items

    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
     Sever
    -0.09
    æIJģ
    -0.09
    å§IJ妹
    -0.09
    .shtml
    -0.09
    äch
    -0.09
    æµ·æ·Ģ
    -0.09
    /reference
    -0.08
    ùng
    -0.08
    æĶ¾åħ¥
    -0.08
    çĩł
    -0.08
    POSITIVE LOGITS
    饱åĴĮ
    0.09
    åĺ´éĩĮ
    0.09
    åıijåħī
    0.08
     satur
    0.08
     DIRECTORY
    0.08
    çŀĢ
    0.08
    éĢĤåIJĪèĩªå·±
    0.08
    干活
    0.08
    é¢ĨåĨĽ
    0.08
    _ev
    0.08
    Activations Density 0.041%

    No Known Activations