© 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. 63521
    Prev
    Next
    INDEX
    Explanations

    "don't", "do", "THAT" with follow-up

    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
    ä¸Ģè·¯ä¸Ĭ
    -0.10
    åIJ¸å¼ķäºĨ
    -0.10
    ä¸Ģè§Ĵ
    -0.10
    åı¯ä»¥è¯´æĺ¯
    -0.09
    åı¯ä»¥è¯´
    -0.09
    åįģåĩłä¸ª
    -0.09
    æıIJä¾Ľä¼ĺè´¨
    -0.09
    离å¼ĢäºĨ
    -0.09
    æĹ¥å¤ľ
    -0.09
    æ¯Ķäºļ
    -0.09
    POSITIVE LOGITS
    ÑĭваÑİÑĤ
    0.10
     обÑĭÑĩно
    0.09
    人们
    0.09
    /people
    0.09
    å«Į
    0.08
    代è¨Ģ
    0.08
    æĪĴ
    0.08
     sharp
    0.08
    çĿ¡çľł
    0.08
    avic
    0.08
    Activations Density 0.293%

    No Known Activations