© 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. 24337
    Prev
    Next
    INDEX
    Explanations

    List of diverse topics

    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
    axter
    -0.09
    ç½ijéĢļ
    -0.08
    .newaxis
    -0.08
    æĻ®éĢļçļĦ
    -0.08
    TRL
    -0.08
    çѱ
    -0.08
    æĻ®éĢļ
    -0.07
    ×ķ×¢
    -0.07
    éħ¬
    -0.07
    ä¼łç»Łäº§ä¸ļ
    -0.07
    POSITIVE LOGITS
    è´¯
    0.08
    建设åĴĮ
    0.08
    çľĩ
    0.08
    å¾Ĺå¾Ī好
    0.08
    åĴĮå°ļ
    0.08
    åŀĤ
    0.08
    å¾Ĺå¾Ī
    0.08
    ÙĩÙĪ
    0.08
    oret
    0.08
    ä»ķ
    0.08
    Activations Density 1.106%

    No Known Activations