© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40401
    Prev
    Next
    INDEX
    Explanations

    tired or not anymore

    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
    Negative Logits
    ç´§å¼ł
    -0.10
    æĦıåIJij
    -0.10
    èĻ½çĦ¶æĺ¯
    -0.09
    æľ¦èĥ§
    -0.09
    Tro
    -0.09
    å»¶æľŁ
    -0.09
    ä¾µçĬ¯
    -0.09
    äºĴ缸
    -0.09
    稳å®ļ
    -0.08
    æģŃåĸľ
    -0.08
    POSITIVE LOGITS
    æĹłå¥Ī
    0.12
    容å¿į
    0.11
    å¿į
    0.11
    被迫
    0.11
    pect
    0.11
    æĴĤ
    0.10
    æĩĴå¾Ĺ
    0.10
    åıªå¾Ĺ
    0.10
    ocking
    0.10
    屡
    0.10
    Activations Density 0.295%

    No Known Activations