© 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. 8842
    Prev
    Next
    INDEX
    Explanations

    occupied and entertained

    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¸ĢéĿ¢
    -0.10
    ÖĦ
    -0.10
    inand
    -0.09
    å±ıèĶ½
    -0.09
    äºŃ
    -0.08
    ç¯ĩ
    -0.08
    奢ä¾Ī
    -0.08
    ç²¾åįİ
    -0.08
    ically
    -0.08
    æ±ĩéĽĨ
    -0.08
    POSITIVE LOGITS
    æľīæĦıä¹ī
    0.10
    å¾Ń
    0.10
    'action
    0.09
     пÑĢеж
    0.09
    满
    0.09
    没äºĨ
    0.09
    åħħå®ŀ
    0.09
    ä¸į满
    0.09
    滿
    0.09
    engo
    0.09
    Activations Density 0.057%

    No Known Activations