© 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. 55642
    Prev
    Next
    INDEX
    Explanations

    waving or wave motion

    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
    纥
    -0.09
    ries
    -0.09
    æĸ°äº¬
    -0.09
    cken
    -0.09
    czy
    -0.08
    åĪ»æĦı
    -0.08
    ä¸Ģäºĭ
    -0.08
    æ¯ıä¸Ģ个人
    -0.08
     Wort
    -0.08
    rus
    -0.08
    POSITIVE LOGITS
     goodbye
    0.11
    dÃŃ
    0.09
    æĭĤ
    0.09
    OTE
    0.09
    æı®
    0.09
    é¼łæłĩ
    0.09
    é£ı
    0.09
     Frem
    0.09
    æĹĮ
    0.08
    оÑĩек
    0.08
    Activations Density 0.006%

    No Known Activations