© 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. 61811
    Prev
    Next
    INDEX
    Explanations

    "the" followed by capitalized words

    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
    coal
    -0.09
     ÑĥÑģл
    -0.09
    Coal
    -0.08
    å¹³çŃī
    -0.08
     chilling
    -0.08
    泯
    -0.08
    æĹłæ¯Ķ
    -0.08
    ain
    -0.08
     bev
    -0.08
     Pix
    -0.08
    POSITIVE LOGITS
    èµ·æĿ¥äºĨ
    0.10
    çľŁäºº
    0.10
    æľ¬è´¨
    0.09
     ÐĴедÑĮ
    0.09
    å¯Ĥå¯ŀ
    0.09
    evin
    0.09
    åıŁ
    0.09
    ä½ĵçİ°äºĨ
    0.08
    ä¸Ģåıª
    0.08
    åģĩæĹ¥
    0.08
    Activations Density 0.030%

    No Known Activations