© 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. 24251
    Prev
    Next
    INDEX
    Explanations

    acknowledgement or uncertainty

    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
    à¹Ģà¸ģร
    -0.09
    _YUV
    -0.09
    claimed
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    çļĦçŃĶæ¡Ī
    -0.08
    algo
    -0.08
     гаÑĢанÑĤи
    -0.08
    aka
    -0.08
    æľīæĦı
    -0.08
    æĥħåķĨ
    -0.08
    POSITIVE LOGITS
    称ä¹ĭ为
    0.10
    æĺ¯å¤ļä¹Ī
    0.09
    æĪij说
    0.09
    äºİæѤ
    0.08
    綦
    0.08
    iously
    0.08
     Äijá»±ng
    0.08
    屿
    0.08
    ç¼¥
    0.08
    ally
    0.08
    Activations Density 0.109%

    No Known Activations