© 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. 60811
    Prev
    Next
    INDEX
    Explanations

    rule proposal revoke postpone order mandated

    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
    éĤij
    -0.09
    æĮª
    -0.09
    æĺ¯ä¸ĢåIJį
    -0.09
    å¸Ĥ人大
    -0.08
    èµ°åĩº
    -0.08
    atu
    -0.08
    å¸ĤæĶ¿åįı
    -0.08
    å¸Ĥå§Ķ
    -0.08
     '~/
    -0.08
     Legislative
    -0.07
    POSITIVE LOGITS
    å¾µ
    0.11
    æĮĩåįĹ
    0.10
    è¶ĭ
    0.10
    åıijå¸ĥäºĨ
    0.10
    å¾ģæ±Ĥ
    0.10
    æ¿Ĵ
    0.10
    ä½ĵè´¨
    0.09
    Ø´ÙĨ
    0.09
    é¢ģå¸ĥ
    0.09
    æīĢè°ĵ
    0.09
    Activations Density 0.116%

    No Known Activations