© 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. 40411
    Prev
    Next
    INDEX
    Explanations

    burn wounds and treatment

    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
    hood
    -0.09
     пÑĢоÑģ
    -0.09
    æĮ¥
    -0.09
    ä¸įä¸ĭ
    -0.09
    ç¢ĵ
    -0.08
    æı®
    -0.08
    åĿļ飧
    -0.08
    碰æĴŀ
    -0.08
    å§Ķåijĺ
    -0.08
    ниÑĨа
    -0.08
    POSITIVE LOGITS
    åŁ¹
    0.10
    ingly
    0.10
    out
    0.09
    ä¹ĭä½Ļ
    0.09
    outing
    0.09
    æ¾Ī
    0.09
     Hispan
    0.09
    isp
    0.08
    ä¸įä»ħåı¯ä»¥
    0.08
     Gallagher
    0.08
    Activations Density 0.013%

    No Known Activations