© 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. 52053
    Prev
    Next
    INDEX
    Explanations

    today or dates

    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
    ä¹ĭåĬĽ
    -0.09
    çİĻ
    -0.09
    ä¼ĹæīĢ
    -0.09
    èĵ®
    -0.09
    ĶåĽŀ
    -0.09
    èݲ
    -0.08
    该æ¡Ī
    -0.08
    å®ŀä¹ł
    -0.08
    æĽ´æĸ°
    -0.08
    ulet
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.15
    ä»Ĭ天
    0.12
    è¯ŀ
    0.11
     today
    0.11
     TODAY
    0.10
    UPI
    0.10
    .today
    0.10
     heute
    0.10
     Today
    0.10
     hoje
    0.10
    Activations Density 0.072%

    No Known Activations