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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36818
    Prev
    Next
    INDEX
    Explanations

    surgical infections and medical procedures

    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
    åĽ¢è´Ń
    -0.09
    oplay
    -0.09
     DOC
    -0.09
    ë§Ŀ
    -0.09
    çĦ¦
    -0.09
    éĺĢ
    -0.08
    æĵįæݧ
    -0.08
    饱åĴĮ
    -0.08
    é«ĺåĩº
    -0.08
    åĽ¢åijĺ
    -0.08
    POSITIVE LOGITS
    ä¸Ģéģĵ
    0.11
    æĹ·
    0.10
     Fry
    0.10
    éĴ¢ç»ĵæŀĦ
    0.10
    æ¢ĵ
    0.09
    éľı
    0.09
    åIJ¯è¿ª
    0.09
    çļĦåį°è±¡
    0.09
    æľ¨æĿIJ
    0.09
    opper
    0.09
    Activations Density 0.328%

    No Known Activations