© 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. 16625
    Prev
    Next
    INDEX
    Explanations

    pregnant individuals, illness, obesity

    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
    æķħ乡
    -0.09
    æ¦ľ
    -0.09
    .enumer
    -0.08
    ä¸¤å¼ł
    -0.08
    è¿Ļçīĩ
    -0.08
    çĥ½
    -0.08
    ä¸ī峡
    -0.08
    ä¸Ģç¯ĩ
    -0.08
     Tags
    -0.08
     sexes
    -0.07
    POSITIVE LOGITS
    家ä¼Ļ
    0.15
    人家
    0.12
    人士
    0.11
    ä¹ĭ人
    0.11
     individuals
    0.11
    äººåľ¨
    0.11
    NESS
    0.11
    人们
    0.10
    人éĥ½
    0.10
    人大
    0.10
    Activations Density 0.265%

    No Known Activations