© 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. 59370
    Prev
    Next
    INDEX
    Explanations

    the following location

    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
    ç¥ĸåĽ½
    -0.09
    folk
    -0.09
    åIJĮæľŁ
    -0.09
    交代
    -0.09
    éĤ£æł·çļĦ
    -0.09
    幸
    -0.09
    TagName
    -0.08
    åѦåĪ°
    -0.08
    éķĬ
    -0.08
    incess
    -0.08
    POSITIVE LOGITS
    è¸ı
    0.09
    eria
    0.08
    æ¯ıä¸Ģ
    0.08
    æľĢåħ·
    0.08
    主æĿĥ
    0.08
    æ¯ı个
    0.08
    äºĨåĩł
    0.08
    åıijå±ķéĺ¶æ®µ
    0.08
    most
    0.08
    *
    0.08
    Activations Density 0.134%

    No Known Activations