© 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. 60602
    Prev
    Next
    INDEX
    Explanations

    missed it

    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
    ityEngine
    -0.10
    赶
    -0.09
    éĢ¼
    -0.09
    ieÅĦ
    -0.09
    æİ¥åIJ¬
    -0.09
    .tie
    -0.08
    èµ¢å¾Ĺ
    -0.08
    cling
    -0.08
    ä¸ĸçķĮä¸Ģæµģ
    -0.08
    иÑĤеÑģÑĮ
    -0.08
    POSITIVE LOGITS
     earlier
    0.11
    éŀį
    0.10
    è¿Ļä¸ĢåĪĩ
    0.08
    棹
    0.08
    ä¸ĭ乡
    0.08
    éľĩåĬ¨
    0.08
    éĵĭ
    0.08
    精彩
    0.08
    ikel
    0.08
     sal
    0.08
    Activations Density 0.018%

    No Known Activations