© 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. 670
    Prev
    Next
    INDEX
    Explanations

    yearly events and celebrations

    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
    chal
    -0.09
    å¾Īéķ¿
    -0.09
    åĸij
    -0.09
    mary
    -0.08
    ä½łæĢİä¹Ī
    -0.08
    mant
    -0.08
    éķ¶åµĮ
    -0.08
    马æĭī
    -0.08
    éĤ£ä¸ªæŶåĢĻ
    -0.08
    ascript
    -0.08
    POSITIVE LOGITS
    å¾Ģå¹´
    0.13
    æ¯ıå¹´
    0.12
    æ¯ıå¹´éĥ½
    0.11
    ä¸Ģå¹´ä¸Ģ度
    0.10
    顶
    0.10
    æį§
    0.09
    å±Ī
    0.09
    quit
    0.09
    ansa
    0.09
    æ¯ıéĢ¢
    0.09
    Activations Density 0.119%

    No Known Activations