© 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. 40037
    Prev
    Next
    INDEX
    Explanations

    BRCA, cancer, Australia, Four Horsemen

    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
    åѤ
    -0.11
    åĩ¸
    -0.11
    ä»»æĢ§
    -0.10
    åįķ纯çļĦ
    -0.09
    tors
    -0.09
    ibri
    -0.09
    çªģ
    -0.09
    å¥ł
    -0.08
    æĶ¾çľ¼
    -0.08
    è´£ç¼ĸ
    -0.08
    POSITIVE LOGITS
    ä¸ĢæľŁ
    0.09
    äºĨä¸Ģåľº
    0.09
     uniqueness
    0.08
    .abort
    0.08
    ł
    0.08
    ованиÑı
    0.08
     dip
    0.08
    ths
    0.08
    ces
    0.08
    æĸ°è¥¿
    0.08
    Activations Density 0.003%

    No Known Activations