© 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. 8276
    Prev
    Next
    INDEX
    Explanations

    lucky winner or recipient

    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
    èĤ¥èĥĸ
    -0.10
    idth
    -0.09
    ä¸įæĺİçĻ½
    -0.08
    ç©¿è¡£
    -0.08
     yön
    -0.08
     minors
    -0.08
    ä¸ºä½ł
    -0.08
     haystack
    -0.08
     Independence
    -0.08
    èĩ´åĬĽäºİ
    -0.08
    POSITIVE LOGITS
    幸è¿IJ
    0.12
    å¾ĹäºĨ
    0.10
    æľī幸
    0.10
    èį£å¹¸
    0.10
    åı¯ä»¥èİ·å¾Ĺ
    0.10
    èµĦæł¼
    0.10
    åıĹéĤĢ
    0.10
     lucky
    0.10
    èİ·æī¹
    0.09
    æĹ¶æľº
    0.09
    Activations Density 0.123%

    No Known Activations