© 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. 60596
    Prev
    Next
    INDEX
    Explanations

    processes and outcomes

    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
    ä¼Łå¤§çļĦ
    -0.10
    æĪĸå¤ļ
    -0.09
     foul
    -0.09
    .ops
    -0.09
    管çIJĨå±Ģ
    -0.09
    .checkNotNull
    -0.09
    ubs
    -0.09
    ä¿ĿæĮģçĿĢ
    -0.09
    å¸Ńåį·
    -0.09
    ÙĨاÙĨ
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
    ä¸İåıijå±ķ
    0.10
    åĴĮåıijå±ķ
    0.10
    çªĹå¤ĸ
    0.10
     ÙĪØ¥
    0.09
    à¹ģละà¸ģาร
    0.09
    å¼ĢæĿ¥
    0.09
    好
    0.08
    åĩºä¼ļ
    0.08
    ä¸Ńå¿ĥåŁİåĮº
    0.08
    Activations Density 1.208%

    No Known Activations