© 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. 35931
    Prev
    Next
    INDEX
    Explanations

    modern or current time

    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»İåݻ年
    -0.13
    两年åīį
    -0.12
    è¿ijä¸īå¹´
    -0.12
    è¿ij两年
    -0.12
    åįģå¹´åīį
    -0.11
    两年
    -0.11
    æĺİå¹´
    -0.10
    æĸ°çļĦä¸Ģå¹´
    -0.10
    è¿Ļ两年
    -0.10
    ä¸Ģå¹´å¤ļ
    -0.10
    POSITIVE LOGITS
    ä»Ĭ天
    0.17
    ä»ĬæĹ¥
    0.16
     today
    0.14
     modern
    0.14
    çݰ代
    0.14
    èĩ³ä»Ĭ
    0.13
    çı¾ä»£
    0.13
    åIJİæĿ¥
    0.13
    ä»Ĭ天çļĦ
    0.13
    Today
    0.13
    Activations Density 0.308%

    No Known Activations