© 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. 12292
    Prev
    Next
    INDEX
    Explanations

    you followed by verbs

    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
    亡
    -0.11
    篷
    -0.11
    çĺª
    -0.10
    åħŃåIJĪ
    -0.10
    eren
    -0.10
    çĮ¿
    -0.10
    åıĻ
    -0.09
     lear
    -0.09
     stead
    -0.09
    éģ´
    -0.09
    POSITIVE LOGITS
    ç¿»å¼Ģ
    0.09
     Fav
    0.08
     pur
    0.08
    çłĶ究éĻ¢
    0.08
    ç»Ĩç»Ĩ
    0.08
    çľĭä¸Ģä¸ĭ
    0.08
    ä»Ķç»Ĩ
    0.08
    èĢĥå¯Ł
    0.08
    ä¸įçĽ¸ä¿¡
    0.08
     sá»ijng
    0.08
    Activations Density 0.031%

    No Known Activations