© 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. 3067
    Prev
    Next
    INDEX
    Explanations

    copyrighted file

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ®
    -0.09
    ä¸įå¾Ĺ
    -0.09
    ä¸¤å¼ł
    -0.09
    éĬ·
    -0.09
    ä¼łéĹ»
    -0.08
    滢
    -0.08
    ä½Ī
    -0.08
    æĭĹ
    -0.08
    ä¸Ńç¾İ
    -0.08
    -eslint
    -0.08
    POSITIVE LOGITS
    ÖĦ
    0.09
    åѤç«ĭ
    0.09
    icit
    0.09
    ä¹ĭ乡
    0.08
    æ¸ļ
    0.08
    ä¸ĢåĿĹ
    0.08
    夫人
    0.08
    ÙĪÙĥ
    0.08
     copyrighted
    0.08
    çıŃ
    0.08
    Activations Density 0.002%

    No Known Activations