© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38275
    Prev
    Next
    INDEX
    Explanations

    shipyard, quarry, shop, building, atelier

    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
    飵
    -0.09
    ä»ħ代表
    -0.09
    çĶŁäº§åİĤ家
    -0.09
     Ur
    -0.08
    dap
    -0.08
    æķ´ä¸ª
    -0.08
    忧èĻij
    -0.08
    鼩
    -0.08
     ìŬ
    -0.08
    æĻ¶ä½ĵ
    -0.08
    POSITIVE LOGITS
    ifu
    0.10
    å·¥ä½ľç«Ļ
    0.10
    让æ¶Īè´¹èĢħ
    0.09
    主任
    0.09
    æĸ°ä¸ŃåĽ½
    0.09
    æľīéĻIJ责任
    0.08
    工人
    0.08
    side
    0.08
    Localized
    0.08
    ughs
    0.08
    Activations Density 0.047%

    No Known Activations