© 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. 12355
    Prev
    Next
    INDEX
    Explanations

    positive experiences and challenges

    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
    æĮij
    -0.09
    çįł
    -0.08
    æĥ¶
    -0.08
     sanction
    -0.08
    è¾°
    -0.08
    è¿Ļæĺ¯
    -0.08
    åĪ¶è£ģ
    -0.08
    _TP
    -0.08
    ×ķ×¢
    -0.08
    ä¸Ģæīĭ
    -0.08
    POSITIVE LOGITS
    ä¸įå°ıçļĦ
    0.11
    å®ŀå®ŀåľ¨åľ¨
    0.09
     должноÑģÑĤ
    0.09
    ç±³ç²ī
    0.09
     ÙĦÙĦغا
    0.09
    æīĢåľ¨
    0.09
    yms
    0.08
    ãģ©ãģĵãĤį
    0.08
    æĹ¥å¸¸
    0.08
    ä¸įå°ı
    0.08
    Activations Density 0.136%

    No Known Activations