© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    awarded or given to

    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
    央
    -0.10
    ä¸Ń央
    -0.09
    æij¸
    -0.09
     centrally
    -0.09
    central
    -0.09
    çľģéĴ±
    -0.08
     central
    -0.08
    æĪIJéķ¿ä¸º
    -0.08
    åħ¨ç¤¾ä¼ļ
    -0.08
    å®ī康
    -0.08
    POSITIVE LOGITS
    æİĪäºĪ
    0.10
    é¢ģåıij
    0.10
    çļĦæľĢä½³
    0.10
    æľīæĿ¡ä»¶çļĦ
    0.09
    éĢĴç»Ļ
    0.09
    ç»ĻäºĨ
    0.09
    çļĦ对象
    0.09
     kepada
    0.09
    象
    0.09
    交æİ¥
    0.09
    Activations Density 0.055%

    No Known Activations