© 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. 63759
    Prev
    Next
    INDEX
    Explanations

    religious leaders and figures

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hei
    -0.10
    æļ´
    -0.09
    ä¸įåĩº
    -0.09
    èĩªçIJĨ
    -0.08
    è®°ä½ı
    -0.08
    æİ£
    -0.08
    åĥµ
    -0.08
    çĤ«èĢĢ
    -0.08
    åģľæ»ŀ
    -0.08
    èļĢ
    -0.08
    POSITIVE LOGITS
    èģĮä¸ļéģĵå¾·
    0.11
    主æĮģ
    0.10
    æ¯ıåij¨
    0.10
    沫
    0.09
    çļĦ带é¢Ĩä¸ĭ
    0.09
    çĪ·
    0.09
    åĽ¢ä½ĵ
    0.09
    åĽ¢
    0.09
    æªĢ
    0.09
    æ³ķå¸Ī
    0.09
    Activations Density 0.067%

    No Known Activations