© 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. 63875
    Prev
    Next
    INDEX
    Explanations

    qualified health care professional

    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
    èĮ«èĮ«
    -0.09
    èĴ¿
    -0.09
    Susp
    -0.09
     Dictionary
    -0.09
    çĴŀ
    -0.09
    鸿
    -0.09
     ribbon
    -0.09
    çļĩåĨł
    -0.09
    梧
    -0.09
    æIJ¬å®¶
    -0.09
    POSITIVE LOGITS
    ponder
    0.12
    Played
    0.09
    anon
    0.08
    æĺ¯æĢİæł·
    0.08
    STM
    0.08
    ç£ħ
    0.08
    uja
    0.08
    è¿İæİ¥
    0.08
    éĽĨèģļ
    0.08
    nets
    0.08
    Activations Density 0.002%

    No Known Activations