© 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. 588
    Prev
    Next
    INDEX
    Explanations

    left ventricle dysfunction

    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
    èĻı
    -0.11
    æīİ
    -0.10
    ä¸ĢåĪĢ
    -0.10
    åīĥ
    -0.10
    èĢĨ
    -0.09
    çĪ½
    -0.09
    æĭ¨
    -0.09
    xAB
    -0.09
    èĪĶ
    -0.09
    /cat
    -0.09
    POSITIVE LOGITS
    æ²Į
    0.11
    åĬ¨æĦŁ
    0.09
    æľºèĥ½
    0.09
    çĵ£
    0.09
    çĻ¾ä¸ĩ
    0.09
     Gund
    0.09
     gö
    0.08
    å¿ĥèĦı
    0.08
    å¿¡
    0.08
    æ»Ĥ
    0.08
    Activations Density 0.281%

    No Known Activations