© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    questions and requests for help

    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
     Alibaba
    -0.09
    ìĤ¬ë¥¼
    -0.09
    ï¼ļ↵↵
    -0.09
    夯
    -0.09
    æĻ¯
    -0.09
    æľīä¸Ģ次
    -0.08
    è·Łä½ł
    -0.08
    åIJĦç§įåIJĦæł·
    -0.08
    滥
    -0.08
    /grpc
    -0.08
    POSITIVE LOGITS
    使æĪij
    0.11
    æŀIJ
    0.10
    ç«Łæĺ¯
    0.09
    åĪį
    0.09
    (er
    0.08
    é¢łè¦Ĩ
    0.08
    å¦Ĥä½ķ
    0.08
    æĪijåıĪ
    0.08
    çļĦéĩįè¦ģæĢ§
    0.08
     stocking
    0.08
    Activations Density 1.649%

    No Known Activations