© 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. 47584
    Prev
    Next
    INDEX
    Explanations

    "top of", "questions was", "particular function"

    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
    æµĶ
    -0.10
    ç»Ĩèĩ´
    -0.09
    æľīéĴĪ对æĢ§
    -0.09
    à¦ļ
    -0.09
    ä¸į平衡
    -0.08
    YLE
    -0.08
    èĥĢ
    -0.08
    aket
    -0.08
    åıĪ
    -0.08
    屿
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.12
    缮åħī
    0.10
    çļĦä¸Ģ项
    0.09
    ä¸ĢåĪĢ
    0.09
    åijĥ
    0.09
    åħ¶ä¸ŃåĮħæĭ¬
    0.09
    ä¹ĭä¸Ģ
    0.09
    ä¸įåı¯ç¼ºå°ij
    0.09
    å°ijä¸įäºĨ
    0.09
    èĴ½
    0.08
    Activations Density 0.452%

    No Known Activations