© 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. 56170
    Prev
    Next
    INDEX
    Explanations

    LEGO, Pen, spanking, swimming, hive

    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
    梵
    -0.08
    ä½łä»¥ä¸º
    -0.08
    ä¼¼çļĦ
    -0.08
    åīij
    -0.08
    æĪIJ人
    -0.08
     complementary
    -0.08
    urations
    -0.08
    é£Łåĵģèį¯åĵģ
    -0.07
     dame
    -0.07
     sop
    -0.07
    POSITIVE LOGITS
    论åĿĽ
    0.10
    èµĦ
    0.09
    èĬĹ
    0.08
    è´¨éĩıéĹ®é¢ĺ
    0.08
    è¿Ļ两个
    0.08
    åįļ客
    0.08
    ç²¾çĽĬ
    0.08
    åĩºåı°äºĨ
    0.08
    头æĿ¡
    0.08
    æĬĬè¿Ļ个
    0.08
    Activations Density 0.301%

    No Known Activations