© 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. 61566
    Prev
    Next
    INDEX
    Explanations

    being followed by a past participle

    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
    onet
    -0.09
    奥巴
    -0.09
    æĹłåĬĽ
    -0.08
    ä¸įèĩ³äºİ
    -0.08
    说ä¸įå®ļ
    -0.08
    ÑģкоÑĢ
    -0.08
    第ä¸ĢæĿ¡
    -0.08
    èĶº
    -0.08
    为äºĨ让
    -0.08
    æĽ¾åľ¨
    -0.08
    POSITIVE LOGITS
    ä»ĸå°±
    0.09
    æݨåIJij
    0.09
    ä¸Ńåħ³
    0.09
    uffed
    0.09
     Dou
    0.09
     Hispan
    0.09
    æīĵéĢłæĪIJ
    0.09
    å¾Ī好çļĦ
    0.09
    ä¸ĵä¸ļåĮĸ
    0.09
    åħħåĪĨ
    0.09
    Activations Density 0.024%

    No Known Activations