© 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. 29483
    Prev
    Next
    INDEX
    Explanations

    South African names and places

    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
    iju
    -0.09
    OwnProperty
    -0.09
    说æĺİ书
    -0.09
    owy
    -0.09
    -doc
    -0.09
    认è¯ĨåĪ°
    -0.09
    .ft
    -0.08
    æĥ³çĿĢ
    -0.08
    OUS
    -0.08
    两ç§į
    -0.08
    POSITIVE LOGITS
    头çļ®
    0.10
    缯
    0.10
    åıªæľīä¸Ģ个
    0.09
    æŁĺ
    0.09
    ä¸ŃåѦ
    0.09
     Gale
    0.09
    æ§Ń
    0.09
    éķĿ
    0.09
    ä¸ĸä¿Ĺ
    0.09
    çłĸ
    0.08
    Activations Density 0.033%

    No Known Activations