© 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. 57513
    Prev
    Next
    INDEX
    Explanations

    today, date, and time indicators

    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
    æŃ¤æ¬¡
    -0.12
    æѤæŶ
    -0.12
    è¿Ļ两年
    -0.11
    è¿ĻæŶ
    -0.11
    åĪ°æŶåĢĻ
    -0.11
    è¿ĻæŶåĢĻ
    -0.11
    æѤæĻĤ
    -0.10
    å±ĬæŶ
    -0.10
    æѤåīį
    -0.10
    è¿Ļ次
    -0.10
    POSITIVE LOGITS
    æĺ¨æĹ¥
    0.12
    æĺİ天
    0.11
    Yesterday
    0.11
    (today
    0.10
    æĺİæĹ¥
    0.10
    ä¸ĬåįĪ
    0.09
    ä»ĬæĹ¥
    0.09
    utar
    0.09
    today
    0.09
    utable
    0.09
    Activations Density 0.119%

    No Known Activations