© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9722
    Prev
    Next
    INDEX
    Explanations

    upcoming topics and updates

    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
    éķĤ
    -0.10
    ç§ijæĬĢèĤ¡ä»½
    -0.09
    éĿ¢åŃIJ
    -0.08
    ç¥Ģ
    -0.08
    è¹ļ
    -0.08
    åľ¨æĪijåĽ½
    -0.08
    æł½
    -0.08
    0
    -0.08
    åıijæĮ¥äºĨ
    -0.08
    纯
    -0.08
    POSITIVE LOGITS
    æĺİ天
    0.14
    ä¸ĭä¸Ģç¯ĩ
    0.11
    æŃ£å¼ı
    0.10
    æĽ´å¤ļ精彩
    0.10
    _managed
    0.10
    æĺİæĹ¥
    0.10
     tomorrow
    0.10
    ingham
    0.10
    ocking
    0.09
    åįļ客
    0.09
    Activations Density 0.042%

    No Known Activations