© 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. 37009
    Prev
    Next
    INDEX
    Explanations

    cervical screening and pap smears

    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
    æ²®
    -0.10
    éķĽ
    -0.10
    ä¸ĢèĤ¡
    -0.10
    UMB
    -0.09
    å®Ĺ
    -0.09
    æĿ¡çº¦
    -0.09
    ä¼ŀ
    -0.09
    ÑĥлÑĮ
    -0.09
    ç¹ĩ
    -0.09
    æ¸Ĺ
    -0.09
    POSITIVE LOGITS
    æ´»
    0.10
    ä¸¤å¼ł
    0.10
    æ£Ģ
    0.10
    çİ»
    0.10
    ä¿Ĺ
    0.09
    æĻļ
    0.09
    å¹³åĿĩæ¯ı
    0.08
    ç¯
    0.08
    å¼Ĥ常
    0.08
    çļĦ女人
    0.08
    Activations Density 0.204%

    No Known Activations