© 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. 22442
    Prev
    Next
    INDEX
    Explanations

    West Ham, Pharrell Williams, George Will

    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
    åĿŀ
    -0.08
    ey
    -0.08
     mall
    -0.08
    esco
    -0.08
    erness
    -0.08
    å·´æĸ¯
    -0.08
     Wu
    -0.08
    ician
    -0.08
    icine
    -0.08
     ters
    -0.08
    POSITIVE LOGITS
    åIJij社ä¼ļ
    0.10
    PEAR
    0.10
    æĺŁçº§éħĴåºĹ
    0.10
    developers
    0.09
    æĶ»åĬ¿
    0.09
    ãĥĢãĥ¡
    0.08
    FAULT
    0.08
    AMY
    0.08
    åŃĺ款
    0.08
     ClassNotFoundException
    0.08
    Activations Density 0.004%

    No Known Activations