© 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. 30743
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    å¾Īé«ĺåħ´
    -0.11
    ç»Īäºİ
    -0.10
    裳
    -0.10
    ä¸įèĥ½åĨį
    -0.10
     ìĿ¼ëĭ¨
    -0.09
    å¾Īå¼Ģå¿ĥ
    -0.09
    å¸ĮæľĽèĥ½
    -0.09
    èĢģ人家
    -0.09
    itti
    -0.09
    å¯ĦãģĽ
    -0.09
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥
    0.15
    ä¹Łåı¯
    0.15
     вмеÑģÑĤ
    0.12
     instead
    0.12
    èĢĮæĺ¯
    0.11
    ãĤĤãģ£ãģ¨
    0.11
    ä»£æĽ¿
    0.11
    instead
    0.11
    æį¢æĪIJ
    0.11
     Instead
    0.10
    Activations Density 0.136%

    No Known Activations