© 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. 29491
    Prev
    Next
    INDEX
    Explanations

    place names ending in ville, port, falls, ark, ington

    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
    æĦıè§ģåıįé¦Ī
    -0.09
    èĬĤ缮ä¸Ń
    -0.09
    åĿŀ
    -0.09
     век
    -0.09
    éķ¿åŁİ
    -0.08
    æĢ»æĶ¶åħ¥
    -0.08
    isa
    -0.08
    inqu
    -0.08
     possession
    -0.08
    asser
    -0.08
    POSITIVE LOGITS
    anoi
    0.09
    è¹ĩ
    0.09
    éĥ¢
    0.09
    æľ¨
    0.09
    ariat
    0.09
    unes
    0.09
    uent
    0.09
    èģļåIJĪ
    0.09
    èŁª
    0.08
    illus
    0.08
    Activations Density 0.016%

    No Known Activations