© 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. 16739
    Prev
    Next
    INDEX
    Explanations

    God, first day, Structure, abstract, Ore

    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
    quot
    -0.08
     quot
    -0.08
    深深çļĦ
    -0.08
     loyalty
    -0.08
    åĨľåİĨ
    -0.08
     berlin
    -0.08
    uhl
    -0.07
     olacaģı
    -0.07
    ç½ķ
    -0.07
    acs
    -0.07
    POSITIVE LOGITS
    âļĵ
    0.10
    ä¼ĬåĪ©
    0.09
    éĥ½è¯´
    0.09
    ç¬ķ
    0.08
    åľ¨çݩ家ä¸Ń
    0.08
    ä¹Łä¸įçŁ¥éģĵ
    0.08
    æĺİæĹ¥
    0.08
     conc
    0.08
    à§į
    0.08
    æĿŁ
    0.08
    Activations Density 0.082%

    No Known Activations