© 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. 59309
    Prev
    Next
    INDEX
    Explanations

    disease and health

    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
    åĪ½
    -0.09
    æ£ķèī²
    -0.09
     vain
    -0.09
    éĢ¼
    -0.09
    æĶ¶ç´§
    -0.09
    èĥĮçĿĢ
    -0.08
    è¿«
    -0.08
    æļ´
    -0.08
    åįłçĶ¨
    -0.08
    为å¥ijæľº
    -0.08
    POSITIVE LOGITS
    çĸ¾çĹħ
    0.18
    çĸ¾çĹħçļĦ
    0.17
     disease
    0.16
    æ²»çĹħ
    0.12
     Disease
    0.12
     diseases
    0.12
    çĶŁçĹħ
    0.12
     dise
    0.12
    åģ¥åº·
    0.11
    çĹħçĹĩ
    0.11
    Activations Density 0.270%

    No Known Activations