© 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. 64124
    Prev
    Next
    INDEX
    Explanations

    cholesterol and hypercholesterolemia

    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
    éĵĦ
    -0.09
    mares
    -0.09
    nder
    -0.09
    èĪĮ
    -0.09
    ToSelector
    -0.09
    yon
    -0.09
    ள
    -0.09
     Det
    -0.08
    é£İåIJ¹
    -0.08
    bles
    -0.08
    POSITIVE LOGITS
    åħħå®ŀ
    0.10
    åį¿
    0.09
    ä¿ļ
    0.09
     Vance
    0.09
    éĻĽ
    0.09
    å¥Ĺé¤IJ
    0.08
    à¸ģระà¸Ĺ
    0.08
    èĥª
    0.08
    ä¸Ģ楼
    0.08
     Enlight
    0.08
    Activations Density 0.083%

    No Known Activations