© 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. 60632
    Prev
    Next
    INDEX
    Explanations

    you verb

    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
    æĹ©åľ¨
    -0.09
    plementation
    -0.09
    çĮ·
    -0.08
    天河
    -0.08
    oti
    -0.08
    åħ±åIJĮåıijå±ķ
    -0.08
    产æĿĥ
    -0.08
    odom
    -0.08
    ç±į
    -0.08
    åħ¨éĿ¢åıijå±ķ
    -0.08
    POSITIVE LOGITS
    bury
    0.09
    æĦıä¹īä¸Ĭ
    0.08
    inya
    0.08
    ronym
    0.08
     Vest
    0.08
    æĸ°å½¢åĬ¿
    0.08
    isting
    0.08
    ä½ĵéĩı
    0.08
    uzzi
    0.08
    ä¸Ģè·¯
    0.08
    Activations Density 0.055%

    No Known Activations