© 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. 59359
    Prev
    Next
    INDEX
    Explanations

    annoying things: parking tickets, arguing, bully

    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
    åij¨æģ©
    -0.09
    ä¸įéĶĻçļĦ
    -0.09
    æµ£
    -0.08
    ä¸įä¼ļæľī
    -0.08
    çĨı
    -0.08
    ç«
    -0.08
    elsen
    -0.08
    便äºİ
    -0.08
    _DISP
    -0.08
    éĢIJ
    -0.08
    POSITIVE LOGITS
    æĺİæĺİ
    0.09
    çłij
    0.09
    éĢŀ
    0.09
    Ñģка
    0.09
    çĺ¿
    0.08
    .ERR
    0.08
    åľ¨åŃ¦æł¡
    0.08
    çĹ£
    0.08
    ãĥªãĤ¢
    0.08
    ä¿Ŀæ´ģ
    0.08
    Activations Density 0.230%

    No Known Activations