© 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. 63987
    Prev
    Next
    INDEX
    Explanations

    patients, physicians, students, staff

    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
    æĪijåĴĮ
    -0.12
    为广大
    -0.11
    prise
    -0.09
     Ngh
    -0.09
    广大
    -0.09
    为æ°ij
    -0.08
    æĤ¬å¿µ
    -0.08
    leans
    -0.08
    ams
    -0.08
    两大
    -0.08
    POSITIVE LOGITS
     alike
    0.11
    åıĮåIJij
    0.10
    äºĴåĬ¨
    0.10
    è¿Ļ对
    0.10
    çļĦåħ³ç³»
    0.10
    èĩªèº«çļĦ
    0.09
    èĩ¾
    0.09
    ä¾ı
    0.09
    æµij
    0.09
    èĥĻ
    0.08
    Activations Density 0.096%

    No Known Activations