© 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. 27949
    Prev
    Next
    INDEX
    Explanations

    responsible for

    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
    ÑĢеÑģ
    -0.09
    èĩ´åĬĽ
    -0.08
    涨
    -0.08
    æĻ¨æĬ¥
    -0.08
    èĮħ
    -0.08
    usted
    -0.08
     Vive
    -0.08
     ÐĴлад
    -0.08
    ç¹ģå¿Ļ
    -0.08
    æijĨ
    -0.08
    POSITIVE LOGITS
    æ³ķå¾ĭ责任
    0.10
    ä¸ĩ亿
    0.09
    åķľ
    0.09
    ÑĤÑĢаÑĤ
    0.09
    çķĻä½ı
    0.09
    çħ¨
    0.09
    ãĥĪãĥª
    0.09
    浪
    0.09
    лоÑĤ
    0.08
    æĽ´é«ĺ
    0.08
    Activations Density 0.023%

    No Known Activations