© 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. 22966
    Prev
    Next
    INDEX
    Explanations

    minutes, over, course, or span

    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
    羿
    -0.09
    oup
    -0.09
    æİĺ
    -0.08
    æĹ¥åīį
    -0.08
    代表
    -0.08
    éķ¿å¤§äºĨ
    -0.08
    éĴ¿
    -0.08
    MMdd
    -0.08
    éĹ®éĹ®
    -0.08
    upt
    -0.08
    POSITIVE LOGITS
    漫éķ¿
    0.13
    åİĨæŶ
    0.12
    ç¼ĵæħ¢
    0.12
    ç¼ĵç¼ĵ
    0.11
    Span
    0.11
     Span
    0.11
    éķ¿è¾¾
    0.10
    跨度
    0.10
    è¾ĥéķ¿
    0.10
    æħ¢æħ¢
    0.10
    Activations Density 0.100%

    No Known Activations