© 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. 565
    Prev
    Next
    INDEX
    Explanations

    for [Mac, iPhone, Visual, Windows, Skype]

    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
    æŶèĬĤ
    -0.10
    乡
    -0.10
    æĭ¨
    -0.09
    æĴ©
    -0.09
     tal
    -0.09
    åķ¸
    -0.08
    ofi
    -0.08
    Ãłn
    -0.08
    åĪĢ
    -0.08
    æĹłå£°
    -0.08
    POSITIVE LOGITS
    ä¸įåħį
    0.10
    ä¼łåĩº
    0.09
    downloads
    0.09
    çi
    0.09
    -tm
    0.09
    太åŃIJ
    0.08
    kle
    0.08
     stu
    0.08
    çļĩ家
    0.08
    uria
    0.08
    Activations Density 0.126%

    No Known Activations