© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    chromosomal abnormalities and defects

    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
    åIJĦ个æĸ¹éĿ¢
    -0.10
    å§Ķ
    -0.09
    BED
    -0.08
    uito
    -0.08
    oure
    -0.08
    åķĥ
    -0.08
    çļĦèģĮä¸ļ
    -0.08
    çªģçł´åı£
    -0.08
    å¦ĩ
    -0.08
    ĥģ
    -0.08
    POSITIVE LOGITS
     Pixar
    0.09
    æ®Ľ
    0.09
    .Arg
    0.09
    è´¢ç»ı
    0.09
    éĶ¯
    0.08
    å²Ń
    0.08
    åIJ¸å¼ķæĽ´å¤ļ
    0.08
     Claw
    0.08
    çĤ¯
    0.08
     unh
    0.08
    Activations Density 0.225%

    No Known Activations