© 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. 30402
    Prev
    Next
    INDEX
    Explanations

    soybean and alfalfa

    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
    諮詢
    -0.09
    axed
    -0.09
    isex
    -0.09
    çĶij
    -0.09
    æĿ¿æĿIJ
    -0.09
    æĺŁçº§éħĴåºĹ
    -0.08
    娴
    -0.08
    è¿Ŀç«ł
    -0.08
    åįģ足
    -0.08
    mares
    -0.08
    POSITIVE LOGITS
    eyes
    0.09
    ptoms
    0.09
    æĺ¯ä¸ŃåĽ½
    0.08
    éĩįä¸Ń
    0.08
    涯
    0.08
    éĺ²çģ«
    0.08
    eko
    0.08
    åĴª
    0.08
    èĭ
    0.08
    æĺ¯éŁ©åĽ½
    0.08
    Activations Density 0.009%

    No Known Activations