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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 28062
    Prev
    Next
    INDEX
    Explanations

    excitement and exclamation

    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
    éģ¿å¼Ģ
    -0.11
    åĨ³è®®
    -0.11
    ä¸įåIJĮæĦı
    -0.10
    ologne
    -0.10
    ç«ĭ马
    -0.09
    仨
    -0.09
    èľļ
    -0.09
    éĸĴ
    -0.09
    æĸĻ
    -0.09
    峨
    -0.09
    POSITIVE LOGITS
    æ¿ĢåĬ¨
    0.16
    åħ´å¥ĭ
    0.16
    å°ĸåı«
    0.15
    欢åij¼
    0.14
    å¥Ķè·ij
    0.14
     excitement
    0.13
    æĥĬåĸľ
    0.13
     excl
    0.13
    åĸľæĤ¦
    0.13
    åĸĬ
    0.11
    Activations Density 0.071%

    No Known Activations