© 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. 12180
    Prev
    Next
    INDEX
    Explanations

    how i can / how to

    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
    å¨ĥå¨ĥ
    -0.09
    ç¦ı彩
    -0.08
    jspx
    -0.08
    缴éĢļ车
    -0.08
    éĶ¹
    -0.08
    æľīèī²éĩijå±ŀ
    -0.08
     coal
    -0.08
    绯
    -0.08
    ä¸įä½ı
    -0.08
     gir
    -0.08
    POSITIVE LOGITS
    æł·çļĦ
    0.10
    å¦Ĥä½ķåİ»
    0.10
    ä¸Ģä¸ĭåŃIJ
    0.10
    大æĸ¹
    0.10
     вообÑīе
    0.09
    åģļåĪ°
    0.09
    è¿ĻèĪ¬
    0.09
    èī°è¾Ľ
    0.09
    æł·
    0.09
    ãģĭãĤĤ
    0.09
    Activations Density 0.239%

    No Known Activations