© 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. 6224
    Prev
    Next
    INDEX
    Explanations

    policy discussion

    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
    ä¾ij
    -0.09
    æĢ»æĶ¶åħ¥
    -0.08
     sir
    -0.07
    ä¸įçIJĨ
    -0.07
    tl
    -0.07
    ä¸įä¸Ĭ
    -0.07
    çľī
    -0.07
    olid
    -0.07
    æ¶Ī
    -0.07
     Dut
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.17
    åħ³äºİ
    0.16
    è¿Ļæĸ¹éĿ¢
    0.15
    æѤ类
    0.15
    该项
    0.13
     ÙĦÙĩØ°Ùĩ
    0.13
    æ¶ī足
    0.12
    æѤäºĭ
    0.12
     بشأÙĨ
    0.12
    æŃ¤é¡¹
    0.12
    Activations Density 1.277%

    No Known Activations