© 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. 24143
    Prev
    Next
    INDEX
    Explanations

    certified, approved, licensed, recognized, accredited

    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
     crossorigin
    -0.09
    (CL
    -0.09
    yclopedia
    -0.09
     ÐĺÑģ
    -0.09
    çªľ
    -0.09
    æĪĸå¤ļ
    -0.08
    èѦæĥķ
    -0.08
    æĸ°ä¸Ģè½®
    -0.08
    å¾ģæľį
    -0.08
    virt
    -0.08
    POSITIVE LOGITS
    æ¸łéģĵ
    0.10
    adamente
    0.10
    ably
    0.09
    èĢĮä¸Ķ
    0.09
    æ¯ıå½ĵ
    0.09
    人æīįéĺŁä¼į
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
     Spicer
    0.09
    ä¸Ķ
    0.08
    çļĦæĸ¹å¼ıæĿ¥
    0.08
    Activations Density 0.054%

    No Known Activations