© 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. 31360
    Prev
    Next
    INDEX
    Explanations

    reporting speech or identity

    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
    çļĦ带é¢Ĩ
    -0.09
    ä¸įä¹ı
    -0.08
    æ³®
    -0.08
    _SC
    -0.08
    人家
    -0.08
     Offline
    -0.08
    errs
    -0.08
    ournée
    -0.08
    认
    -0.08
    æķ´è½¦
    -0.08
    POSITIVE LOGITS
    帮ä»ĸ
    0.11
    çĪĨæĸĻ
    0.10
    éļ¶å±ŀäºİ
    0.10
    翼
    0.10
    è°ı
    0.10
    帮å¿Ļ
    0.09
    çºłç¼ł
    0.09
    éĻª
    0.09
    éĻªåIJĮ
    0.09
    æī®æ¼Ķ
    0.09
    Activations Density 0.214%

    No Known Activations