© 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. 12234
    Prev
    Next
    INDEX
    Explanations

    product reviews and walkthroughs

    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
    没éĹ®é¢ĺ
    -0.08
    æľīç§į
    -0.08
    æ¸IJ
    -0.08
    讲课
    -0.08
    æ£Ģç´¢
    -0.08
    èĬĤå¥ı
    -0.08
     billboard
    -0.08
    éĴ§
    -0.07
    ç¬ijè¯Ŀ
    -0.07
     Tick
    -0.07
    POSITIVE LOGITS
    ä½ĵéªĮ
    0.13
    åIJIJ槽
    0.11
     подÑĢоб
    0.10
    åŀ¢
    0.10
    详ç»ĨçļĦ
    0.10
    详ç»Ĩ
    0.10
    é«Ķé©Ĺ
    0.10
     verdict
    0.10
    ç»Ļä½łä»¬
    0.09
    å¿ĥå¾Ĺ
    0.09
    Activations Density 0.182%

    No Known Activations