© 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. 47397
    Prev
    Next
    INDEX
    Explanations

    faith traditions

    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
    è¿Ļå¥Ĺ
    -0.09
    çļĦä¸Ģ项
    -0.09
     Jew
    -0.09
    кий
    -0.09
    è¿Ļåĩłå¹´
    -0.08
    è¿Ļ对
    -0.08
    åĥı个
    -0.08
    ä¸įæĺ¯ä¸Ģ个
    -0.08
    æŃ¤äºº
    -0.08
    æīĢæľīæĥħèĬĤ
    -0.08
    POSITIVE LOGITS
    们
    0.31
    们çļĦ
    0.25
    åĢij
    0.20
    们éĥ½
    0.19
    ëĵ¤
    0.18
    ëĵ¤ìĿĦ
    0.16
    ëĵ¤ìĿĢ
    0.15
    ами
    0.15
    ëĵ¤ìĿ´
    0.15
    sWith
    0.14
    Activations Density 1.068%

    No Known Activations