© 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. 47461
    Prev
    Next
    INDEX
    Explanations

    towns and counties

    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
     недо
    -0.10
    æľ¦èĥ§
    -0.09
    磬
    -0.09
    CESS
    -0.08
    é¢Ħå®ļ
    -0.08
    BUY
    -0.08
    åŀĽ
    -0.08
    кÑĥп
    -0.08
    å¤Ķ
    -0.08
    metic
    -0.08
    POSITIVE LOGITS
    ness
    0.11
    tur
    0.10
    æĢ§çļĦ
    0.09
     ek
    0.09
    tre
    0.09
    tog
    0.09
    æĢ§
    0.09
    shire
    0.08
    tant
    0.08
    tc
    0.08
    Activations Density 0.002%

    No Known Activations