© 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. 29566
    Prev
    Next
    INDEX
    Explanations

    sudden cardiac death, exercise improvements

    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
    å±IJ
    -0.10
    æīĵçĮİ
    -0.09
    åĺĺ
    -0.09
    ä¹Łè®¸æĺ¯
    -0.09
    isoft
    -0.09
    å°ģéĿ¢
    -0.09
    çħ½
    -0.09
    åŁİå¸Ĥ建设
    -0.08
    游çİ©
    -0.08
     Scre
    -0.08
    POSITIVE LOGITS
    warf
    0.11
    æĺİå¹´
    0.09
    å¹´ä¹ĭ
    0.09
    ono
    0.09
    æĬĹçĸ«
    0.08
    æĸ°æīĭ
    0.08
    æĨ¾
    0.08
    èĶ¬
    0.08
    war
    0.08
     bib
    0.08
    Activations Density 0.033%

    No Known Activations