© 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. 16547
    Prev
    Next
    INDEX
    Explanations

    Chinese text

    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
    éĢŁåº¦å¿«
    -0.08
    æĴĴ
    -0.08
    åIJĬ
    -0.08
     ÑģÑĤали
    -0.08
    å°ļ
    -0.08
    ordination
    -0.08
    åĨĴ
    -0.07
    å½Ģ
    -0.07
     FAQ
    -0.07
     tank
    -0.07
    POSITIVE LOGITS
    ilan
    0.11
    æĺ¯åĽ½åĨħ
    0.09
    é©Ń
    0.09
    ãģĬ客æ§ĺ
    0.09
    鹿
    0.09
    请æĤ¨
    0.09
    éĥ½ä¸įæķ¢
    0.09
    å¸Ĥå§Ķ常å§Ķ
    0.09
    ẽ
    0.08
    èµ·åĪ°
    0.08
    Activations Density 0.204%

    No Known Activations