© 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. 26082
    Prev
    Next
    INDEX
    Explanations

    sanitizer or amiodarone

    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
    èµı
    -0.08
    岸边
    -0.08
    (bind
    -0.08
    éļıåIJİ
    -0.08
    yles
    -0.08
    çħ½
    -0.07
     Ivanka
    -0.07
     moll
    -0.07
    å¼ĢæĿ¥
    -0.07
     Levin
    -0.07
    POSITIVE LOGITS
    èĥĮåIJİçļĦ
    0.11
    ç§ĺè¯Ģ
    0.10
    çī¹æľīçļĦ
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.09
    åĨħç½®
    0.09
    æºIJèĩª
    0.09
    ç§ijåѦæĬĢæľ¯
    0.09
    еÑģÑĤÑĮ
    0.09
     sucker
    0.09
    ä¸ŃåIJ«æľī
    0.08
    Activations Density 0.961%

    No Known Activations