© 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. 19448
    Prev
    Next
    INDEX
    Explanations

    social events and gatherings

    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
    æĹħç¨ĭ
    -0.09
    çĶŁäº§è½¦éĹ´
    -0.09
    ONUS
    -0.09
     Bent
    -0.08
    _ASCII
    -0.08
    agoon
    -0.08
    课åłĤæķĻåѦ
    -0.08
     phóng
    -0.08
    ä½ļ
    -0.08
     Heather
    -0.08
    POSITIVE LOGITS
    æĻĥ
    0.09
    ç²¾ç¥ŀæĸĩæĺİ
    0.09
    ä¸įä¸ĭ
    0.08
    ãĥĥãĥĪ
    0.08
    æĪijåıªæĺ¯
    0.08
    -turned
    0.08
    åł¡
    0.08
    æĮŁ
    0.08
    åľºåIJĪ
    0.08
    æĹĹå¸ľ
    0.08
    Activations Density 0.062%

    No Known Activations