© 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. 6101
    Prev
    Next
    INDEX
    Explanations

    License information

    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
    åīįè¾Ī
    -0.10
    å§ijå¨ĺ
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.09
    èģĮ
    -0.08
    ardo
    -0.08
    its
    -0.08
     пÑĢеж
    -0.08
    ús
    -0.08
    ette
    -0.08
     Foster
    -0.08
    POSITIVE LOGITS
    å°±è¿Ļä¹Ī
    0.10
    åīįæıIJæĺ¯
    0.10
    å¿łå®ŀ
    0.09
     доволÑĮ
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    å°±è¿Ļæł·
    0.09
    SEP
    0.09
    å¸Ńåį·
    0.09
    äºĨ大éĩıçļĦ
    0.08
    ãı
    0.08
    Activations Density 0.639%

    No Known Activations