© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57732
    Prev
    Next
    INDEX
    Explanations

    patient describing medical conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ниÑĩ
    -0.10
    éĴ¿
    -0.09
    çĤĴ
    -0.09
    åıijæĮ¥ä½ľçĶ¨
    -0.09
    æĹħç¨ĭ
    -0.09
    çĻ¼æı®
    -0.09
    çĶ»åį·
    -0.09
    帮å¿Ļ
    -0.08
    ни
    -0.08
     Ye
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.11
    èĩ
    0.10
    çļĦæķ´ä½ĵ
    0.10
    ç»ıåİĨ
    0.09
    æľīä¸įåIJĮçļĦ
    0.09
    otta
    0.08
    è¿ĺæľīä¸Ģ个
    0.08
    æĪIJ为ä¸Ģ个
    0.08
    æľīä¸Ģ个
    0.08
    @m
    0.08
    Activations Density 0.326%

    No Known Activations