© 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. 6143
    Prev
    Next
    INDEX
    Explanations

    interview or statement

    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
    ä¸įå¿ĺåĪĿå¿ĥ
    -0.10
    庾
    -0.10
    ä¸ĢåľĪ
    -0.09
    prm
    -0.09
    æĬ¤èº«
    -0.08
    decltype
    -0.08
     ÐŁÐ¾Ñĩем
    -0.08
    笼
    -0.08
    SCO
    -0.08
     adequ
    -0.08
    POSITIVE LOGITS
    .fig
    0.09
    .getAction
    0.09
    è¡ĮåĬ¨
    0.09
    å¢ŀåĬłäºĨ
    0.08
    æ¿ĢåĬ¨
    0.08
     اÙĦÙĨÙģ
    0.08
    è§ģéĿ¢
    0.08
    rosse
    0.08
    æĮĩæĮ¥éĥ¨
    0.08
    æĬĽå¼ĥ
    0.08
    Activations Density 0.017%

    No Known Activations