© 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. 859
    Prev
    Next
    INDEX
    Explanations

    without further ado

    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
    åĵªåĦ¿
    -0.09
    éĤ£ä¹Ī容æĺĵ
    -0.09
    éĢĢç¨İ
    -0.09
    /pm
    -0.09
    ird
    -0.09
    俸
    -0.09
    ä½ķ度
    -0.09
    è¿Ļç§įæĸ¹å¼ı
    -0.08
    åIJĥ饱
    -0.08
    è°ģçŁ¥
    -0.08
    POSITIVE LOGITS
    尽快
    0.15
    紧迫
    0.15
    赶紧
    0.14
    ç«ĭåį³
    0.14
    ç«ĭåĪ»
    0.13
    å°½æĹ©
    0.12
    赶快
    0.12
     immediately
    0.12
    æĢ¥å¿Ļ
    0.11
     hurry
    0.11
    Activations Density 0.070%

    No Known Activations