© 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. 29763
    Prev
    Next
    INDEX
    Explanations

    Beauty Queen crowning

    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
    è¯ĥ
    -0.09
    ãĥĸãĥ«
    -0.09
    ä¾Ľæ±Ĥ
    -0.08
    ì¡°
    -0.08
    ä¸Ńéĵģ
    -0.08
    åģĩæĹ¥
    -0.08
    æĬ
    -0.08
    lox
    -0.07
    æ´»è·ĥ
    -0.07
    .InputStreamReader
    -0.07
    POSITIVE LOGITS
    çıº
    0.11
    黾
    0.11
     bá»Ļ
    0.10
    å¢ŀèµĦ
    0.10
    å²IJ
    0.10
    ç°¸
    0.10
     gown
    0.10
    彩
    0.09
    çIJ¨
    0.09
    æĹĴ
    0.09
    Activations Density 0.085%

    No Known Activations