© 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. 29580
    Prev
    Next
    INDEX
    Explanations

    medical procedures or actions

    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
     scraping
    -0.08
    çĽ¼
    -0.08
    é«ĺå°ļ
    -0.08
    è¿İ
    -0.08
    ä¸Ĭä¸ĭ
    -0.08
    åĩºèī²çļĦ
    -0.08
    lop
    -0.08
    áĥ«
    -0.08
    inent
    -0.08
    åģļå¾Ĺ
    -0.08
    POSITIVE LOGITS
    éĢģåĪ°
    0.13
    交ç»Ļ
    0.13
    æĶ¾åĪ°
    0.12
    åĪĨæŀIJ
    0.11
     поÑĤом
    0.11
    带åĪ°
    0.10
    éĢģç»Ļ
    0.10
    alysis
    0.10
    äºĭåIJİ
    0.10
    带åĽŀ
    0.10
    Activations Density 0.200%

    No Known Activations