© 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. 26195
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    æ´Ĺè¡£æľº
    -0.08
    umbs
    -0.08
    å¦Ĥä½ķåİ»
    -0.08
    æ°Ľ
    -0.07
    æľ«
    -0.07
    è¿
    -0.07
    ä¹Łæĺ¯ä¸Ģç§į
    -0.07
    ãĢĨ
    -0.07
    åºĦ
    -0.07
     recom
    -0.07
    POSITIVE LOGITS
    主èIJ¥
    0.10
    订éĺħ
    0.10
    å®ŀæĥł
    0.09
    åĿļä¿¡
    0.09
    åĴĮæľįåĬ¡
    0.09
     невоз
    0.09
    é«ĺ度éĩįè§Ĩ
    0.09
    haven
    0.09
    æľ¬ç«Ļ
    0.09
    èµ·ä¹ī
    0.09
    Activations Density 0.072%

    No Known Activations