© 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. 16756
    Prev
    Next
    INDEX
    Explanations

    awards ceremony or official announcements

    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
    åŁºæľ¬ä¿¡æģ¯
    -0.09
    æĤĦçĦ¶
    -0.09
    олÑı
    -0.09
    åłµ
    -0.08
    ãĥŃãĥ¼ãĥ³
    -0.08
     consent
    -0.08
     комÑĦоÑĢÑĤ
    -0.08
    åį³å°Ĩ
    -0.08
     Days
    -0.08
    ä¸įå°ij
    -0.08
    POSITIVE LOGITS
    è¯ĦéĢī
    0.13
    é¢ģå¥ĸ
    0.11
    æıŃæĻĵ
    0.11
    æ¿ĢåĬ¨
    0.09
    é¢ģåıij
    0.09
    è¯Ħ审
    0.09
    表彰
    0.09
    æĺŁåħī
    0.09
    å¥ĸ项
    0.09
    æıIJåIJį
    0.09
    Activations Density 0.138%

    No Known Activations