© 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. 18740
    Prev
    Next
    INDEX
    Explanations

    heat on stove or oven

    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
    à¹ĥà¸Ī
    -0.10
    arto
    -0.09
    èĦĨå¼±
    -0.09
    hic
    -0.09
    uela
    -0.09
    axes
    -0.09
    æĤį
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    è²ī
    -0.08
    aterial
    -0.08
    POSITIVE LOGITS
    å¼ºåĽ½
    0.09
    YPE
    0.09
     Roz
    0.09
    è¿ĺæĥ³
    0.08
    éļĹ
    0.08
    isel
    0.08
    nar
    0.08
    AndGet
    0.08
    仿
    0.08
    æĸĩç«łæĿ¥æºIJ
    0.08
    Activations Density 0.002%

    No Known Activations