© 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. 24162
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    å¼ºåĽ½
    -0.11
    åĪ°æŶåĢĻ
    -0.11
    éĺĹ
    -0.09
    åĮĸçļĦ
    -0.09
    å¹´åIJİ
    -0.09
    åĩ¼
    -0.09
    IFY
    -0.09
    æĺ¯ä¸Ģéĥ¨
    -0.09
    _expect
    -0.09
    illed
    -0.09
    POSITIVE LOGITS
    éĤ£å¤©
    0.09
    /month
    0.09
    è¿Ļä¸Ģ天
    0.09
    inals
    0.09
    éĤ£æ¬¡
    0.08
    /end
    0.08
    ÙħÙĤاÙĦات
    0.08
    åŃIJéĩĮ
    0.08
    符
    0.08
    è¿ĩåİ»äºĨ
    0.08
    Activations Density 0.169%

    No Known Activations