© 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. 48730
    Prev
    Next
    INDEX
    Explanations

    playing time or opportunities

    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
    æĬµ
    -0.10
    æŀķ头
    -0.09
    æĿĤ
    -0.09
    ale
    -0.09
    çħ§äº®
    -0.08
     Interview
    -0.08
    åĵģè´¨
    -0.08
    æݬ
    -0.08
    å¿łè¯ļ
    -0.08
    æĬµæĬĹåĬĽ
    -0.08
    POSITIVE LOGITS
    æľºä¼ļ
    0.15
    æľīæľºä¼ļ
    0.13
    çļĦæľºä¼ļ
    0.13
    æ©Łæľĥ
    0.11
     opportunities
    0.11
     Opportunities
    0.11
     opportunity
    0.10
     exposure
    0.09
    çĻ»åľº
    0.09
    鸱
    0.09
    Activations Density 0.082%

    No Known Activations