© 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. 26298
    Prev
    Next
    INDEX
    Explanations

    know that you are aware

    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
    对æĸ¹
    -0.11
    工人
    -0.10
    åĬĽè¿ĺæĺ¯
    -0.10
    ç»ıéªĮ丰å¯Į
    -0.09
    å¿ī
    -0.09
     ÑħоÑĤÑĮ
    -0.08
    å±ŀå®ŀ
    -0.08
    åı¤ä»£
    -0.08
     رجاÙĦ
    -0.08
    让æĤ¨
    -0.08
    POSITIVE LOGITS
    ä¸ŃéĢĶ
    0.09
    æĭŁ
    0.09
    踽
    0.09
    лей
    0.08
    alker
    0.08
    eneg
    0.08
    è¿Ļæĺ¯åĽłä¸º
    0.08
    umo
    0.08
    æĺĻ
    0.08
    ync
    0.08
    Activations Density 0.027%

    No Known Activations