© 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. 26156
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    年产
    -0.09
    æĮĩçĿĢ
    -0.09
    åħ¨ä¸ĸçķĮ
    -0.09
     Ñģвоей
    -0.09
    åĵĪå°Ķ
    -0.09
    æĺŁçIJĥ
    -0.09
    大å¤ļæķ°äºº
    -0.09
    è§IJ
    -0.09
    æĶ¹éĿ©åıijå±ķ
    -0.09
    åIJ¬å®Į
    -0.09
    POSITIVE LOGITS
    çļĦåĽłç´ł
    0.10
    åĽłç´ł
    0.09
    ä¸ĵçĶ¨
    0.09
    æĭ¢
    0.09
     ÑĦакÑĤоÑĢ
    0.09
     role
    0.09
     played
    0.08
    人为
    0.08
    sil
    0.08
     Union
    0.08
    Activations Density 0.202%

    No Known Activations