© 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. 60757
    Prev
    Next
    INDEX
    Explanations

    floating on water surface

    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
    Ñĩик
    -0.11
    å´Ĥ
    -0.10
    è®ĵä»ĸ
    -0.09
    èIJ½åľ¨
    -0.09
    éģįåıĬ
    -0.09
     Auditor
    -0.09
    éĺª
    -0.09
    acus
    -0.09
    IGN
    -0.09
    æģª
    -0.09
    POSITIVE LOGITS
    æ°´éĿ¢
    0.16
    éĿ¢ä¸Ĭ
    0.11
    æµ®åĬ¨
    0.10
    ikon
    0.10
    nı
    0.10
    ç¿ķ
    0.09
    çī¹æĸ¯
    0.09
    å¼ĢéĺĶ
    0.08
    ç½®
    0.08
    æĺł
    0.08
    Activations Density 0.066%

    No Known Activations