© 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. 60594
    Prev
    Next
    INDEX
    Explanations

    among the various

    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
    uran
    -0.10
    æ·¡
    -0.09
    ä¸Ńæľī
    -0.08
    çĶŁæĢģæĸĩæĺİ
    -0.08
    utan
    -0.08
    éħįæľī
    -0.08
    rost
    -0.08
     каждом
    -0.08
    æ¡ĮåŃIJä¸Ĭ
    -0.08
    å±ģ
    -0.08
    POSITIVE LOGITS
    åĬ¡
    0.10
    å·§åIJĪ
    0.10
    çľĭä¸įåĩº
    0.09
    æľºä¼ļ
    0.09
    æ´¥
    0.09
    æ·¬
    0.09
    è°¨
    0.09
    éĤ£éĩĮ
    0.09
    æ¯ķ
    0.08
    æ¶Ķ
    0.08
    Activations Density 0.014%

    No Known Activations