© 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. 878
    Prev
    Next
    INDEX
    Explanations

    surgery and surgical 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
    crew
    -0.10
    лей
    -0.10
    åĪijäºĭ责任
    -0.10
    æ·¹
    -0.10
    蹶
    -0.09
     fray
    -0.09
    欺
    -0.09
    eba
    -0.09
    essaging
    -0.09
    æĩ
    -0.09
    POSITIVE LOGITS
    æīĭæľ¯
    0.22
     surgery
    0.21
     Surgery
    0.17
     surgeries
    0.15
    æľ¯
    0.13
    urgery
    0.13
     surgeons
    0.13
    å¤ĸç§ij
    0.12
     surgical
    0.12
     surgeon
    0.11
    Activations Density 0.388%

    No Known Activations