© 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. 20549
    Prev
    Next
    INDEX
    Explanations

    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
    çī¹æķĪ
    -0.10
    imu
    -0.09
    éĹ®ä»ĸ
    -0.09
    /msg
    -0.09
    æīĺè¿IJ
    -0.08
    建档ç«ĭåį¡
    -0.08
    èĬŃ
    -0.08
    åħ¨è¿ĩç¨ĭ
    -0.08
     Tate
    -0.08
    astle
    -0.08
    POSITIVE LOGITS
    ä»Ĭ天çļĦ
    0.13
    è¿Ļä¸Ģ天
    0.12
    ä»ĬæĹ¥
    0.12
    ä»Ĭ天
    0.11
    æĸ°çļĦä¸Ģ
    0.11
    å½ĵ天
    0.10
     today
    0.10
    ä¸ĢåĪĻ
    0.10
     heute
    0.10
     aujourd
    0.10
    Activations Density 0.132%

    No Known Activations