© 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. 16676
    Prev
    Next
    INDEX
    Explanations

    ultimately leads 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
    æѤæŶ
    -0.11
     Hyde
    -0.10
    ä¸ĢæŶ
    -0.10
    æŃ£å¥½
    -0.10
     ìĿ´ìłľ
    -0.10
    éļıæŶ
    -0.10
    æѤæĻĤ
    -0.10
    ãģĻãģ§ãģ«
    -0.09
    ä»İæѤ
    -0.09
     already
    -0.09
    POSITIVE LOGITS
    è¿ĺæĺ¯è¦ģ
    0.13
    æľĢç»Ī
    0.13
     Ultimately
    0.11
    è¿ĺæĺ¯ä¼ļ
    0.11
    Ultimately
    0.11
    ç»Ī究
    0.11
     ultimately
    0.10
     Eventually
    0.10
     eventually
    0.10
    Eventually
    0.09
    Activations Density 0.064%

    No Known Activations