© 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. 29648
    Prev
    Next
    INDEX
    Explanations

    small/tiny

    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
    æĽ´å¤§çļĦ
    -0.10
    æľĢ大çļĦ
    -0.09
    entic
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.09
    æĦļèł¢
    -0.09
    空åīį
    -0.09
    yre
    -0.09
    åŃĿ
    -0.08
    大å®Ĺ
    -0.08
    人æĸĩ
    -0.08
    POSITIVE LOGITS
    /tiny
    0.15
    /small
    0.14
    tiny
    0.12
     tiny
    0.11
     (\<
    0.11
    -small
    0.11
    ä¸Ģ个å°ı
    0.11
     (<
    0.11
    ä¸įå°ı
    0.10
     Tiny
    0.10
    Activations Density 0.263%

    No Known Activations