© 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. 29503
    Prev
    Next
    INDEX
    Explanations

    stirring or mixing fluids

    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
    ÑģÑĤолÑĮ
    -0.09
    弧
    -0.09
    åIJĦæĸ¹éĿ¢
    -0.08
    æļĤæŶ
    -0.08
    产åĢ¼
    -0.08
    å°±åľ¨
    -0.08
    hait
    -0.08
    udos
    -0.08
    礼仪
    -0.08
    羿
    -0.08
    POSITIVE LOGITS
    æIJħæĭĮ
    0.12
    ä¸ĢéĿ¢
    0.09
    ä¼Ĺ人
    0.08
     Herm
    0.08
    æIJħ
    0.08
    æħ¢
    0.08
    æĬµæĮ¡
    0.08
    亡
    0.08
    åıijå±ķè¶ĭåĬ¿
    0.08
    绣æĪĺ
    0.08
    Activations Density 0.021%

    No Known Activations