© 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. 16797
    Prev
    Next
    INDEX
    Explanations

    comes about

    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
     fancy
    -0.10
     Seam
    -0.09
    istes
    -0.09
    æĬ¬å¤´
    -0.09
    è··
    -0.08
    æľīçĽĬ
    -0.08
    髦
    -0.08
    erner
    -0.08
    æ¯ı次
    -0.08
    éļ¾ä»¥
    -0.08
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.13
    åıĸåĨ³
    0.10
    彤
    0.10
    äºİ
    0.10
    è¿Ļ个ä¸ĸçķĮ
    0.10
    oney
    0.10
    ếp
    0.10
    à¸ĵ
    0.10
     matters
    0.10
    ä»Ģä¹Īäºĭ
    0.09
    Activations Density 0.024%

    No Known Activations