© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52308
    Prev
    Next
    INDEX
    Explanations

    a or the before specific nouns

    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
    å½±åĵįåĬĽçļĦ
    -0.10
    ä¼´
    -0.09
    è¹ĭ
    -0.09
    æĺ¨
    -0.08
    anza
    -0.08
    emen
    -0.08
     PE
    -0.08
     ÑĦигÑĥÑĢ
    -0.08
    æ©ĩ
    -0.08
    QUIT
    -0.07
    POSITIVE LOGITS
    æķ´ä¸ª
    0.12
     Ñģобой
    0.12
    åIJĦ个æĸ¹éĿ¢
    0.11
     entire
    0.11
    å±ĢåĬ¿
    0.11
    æķ´ä¸ªäºº
    0.11
    åħ¶éĹ´
    0.11
    åīįè¡Į
    0.10
    人们çļĦ
    0.10
    æ¯ıä¸Ģ个人
    0.10
    Activations Density 0.176%

    No Known Activations