© 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. 16622
    Prev
    Next
    INDEX
    Explanations

    newspaper weekly edition

    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
    åŃ¥
    -0.09
    ä¸įåIJĥ
    -0.09
    ç»Łè®¡å±Ģ
    -0.09
    ìħĪ
    -0.09
    ä¸įéĶĪ
    -0.09
    æĹ¢èĥ½
    -0.09
    é»ijå¤ľ
    -0.09
    é¢Ħ
    -0.08
     ccp
    -0.08
    ä»ħ次äºİ
    -0.08
    POSITIVE LOGITS
     обÑĭ
    0.10
    ì§ĢìĽIJ
    0.09
     Tanner
    0.09
    iens
    0.08
    è¿Ļä¸ĢåĪ»
    0.08
    æ¡ħ
    0.08
    áĢij
    0.08
    çİ°åŃĺ
    0.08
    çĺª
    0.08
    xin
    0.08
    Activations Density 0.031%

    No Known Activations