© 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. 47452
    Prev
    Next
    INDEX
    Explanations

    form as

    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
    æĭ¿èµ·
    -0.10
    éªĭ
    -0.09
    纵深
    -0.09
    èĶļ
    -0.08
     Tate
    -0.08
    æĬļ
    -0.08
    è¯ł
    -0.08
     Äijoán
    -0.08
    ØŃÙĬ
    -0.08
    ä¸įæĩĤ
    -0.08
    POSITIVE LOGITS
    å¤ļç§įå½¢å¼ı
    0.13
    å½¢å¼ı
    0.11
    ä»»ä½ķå½¢å¼ı
    0.10
    ä½ķç§į
    0.10
    çļĦåIJĦç§į
    0.10
    éĿ¢çĽ®
    0.10
     виде
    0.09
    å½¢æĢģ
    0.09
    via
    0.09
    çļĦå½¢å¼ı
    0.09
    Activations Density 0.267%

    No Known Activations