© 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. 29474
    Prev
    Next
    INDEX
    Explanations

    Brook and Brooke names

    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
    uth
    -0.09
    æĭ³
    -0.09
    BM
    -0.08
    ä¼İ
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    建çŃijæĿIJæĸĻ
    -0.08
    åļ£
    -0.08
    AndPassword
    -0.08
    ongo
    -0.08
    andro
    -0.08
    POSITIVE LOGITS
    ripper
    0.12
    sWith
    0.12
    side
    0.11
    lining
    0.10
    keeper
    0.09
    lined
    0.09
     воÑĤ
    0.09
    ETS
    0.09
    keepers
    0.09
    lines
    0.09
    Activations Density 0.003%

    No Known Activations