© 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. 16578
    Prev
    Next
    INDEX
    Explanations

    providing or addressing 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
    çĦ¶èĢĮ
    -0.10
    å¼Ģ
    -0.09
    泡
    -0.09
    è¿Ļæĺ¯åĽłä¸º
    -0.09
    неÑĨ
    -0.09
     zwar
    -0.09
    äºİæĺ¯
    -0.08
    imbus
    -0.08
    åħ¸åŀĭ
    -0.08
    RI
    -0.08
    POSITIVE LOGITS
    åħ¼é¡¾
    0.11
    æ¼ıæ°´
    0.10
    ä¿ĿæĮģçĿĢ
    0.09
    ä¸įå¿ĺ
    0.09
    äºĨä¸ĢäºĽ
    0.09
     STILL
    0.09
    maf
    0.09
    ::$_
    0.09
    ä¸įæĸŃçļĦ
    0.09
    åħ¶ä»ĸ
    0.09
    Activations Density 0.054%

    No Known Activations