© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    relevance, topic, categories

    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
    éĽ¾
    -0.09
    анÑģ
    -0.09
    ä¸Ģéģĵ
    -0.09
    çĪ±ç¾İ
    -0.09
    æł¹æį®ä¸įåIJĮ
    -0.08
    ynes
    -0.08
    Õ
    -0.08
    /operators
    -0.08
    Ñĭв
    -0.08
    å®ĺ
    -0.08
    POSITIVE LOGITS
    主é¢ĺ
    0.13
    é¢ĺæĿIJ
    0.12
     lĩnh
    0.11
    çļĦ主é¢ĺ
    0.11
    é¢ĨåŁŁçļĦ
    0.11
    è¡Įä¸ļçļĦ
    0.10
    é¢ĨåŁŁ
    0.10
    edom
    0.10
     topics
    0.10
     themes
    0.10
    Activations Density 0.114%

    No Known Activations