© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8449
    Prev
    Next
    INDEX
    Explanations

    federal agencies and organizations

    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
    æĬ¢
    -0.09
     numbered
    -0.09
    åİ¿å§Ķ书记
    -0.09
    æIJ¶
    -0.08
    abox
    -0.08
    æĴ©
    -0.08
    åİ¿æĶ¿åºľ
    -0.08
    åķĨä¼ļ
    -0.08
    ä¿Ŀå®Ī
    -0.08
    å®ģåİ¿
    -0.08
    POSITIVE LOGITS
     ÙĪج
    0.10
    grün
    0.09
    å¿ĥ缮
    0.09
    ç¾İ丽
    0.09
    ä¸įè¿ľ
    0.09
    ä¼ļåIJĮ
    0.08
    讽
    0.08
    ENCH
    0.08
     بغ
    0.08
     Cutter
    0.08
    Activations Density 0.038%

    No Known Activations