© 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. 35880
    Prev
    Next
    INDEX
    Explanations

    Turin

    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
    anken
    -0.10
    ä¸ĢåĪ»
    -0.10
    èĩ¾
    -0.09
    åħħåĪĨèĤ¯å®ļ
    -0.09
    æĽ´ä½İ
    -0.09
    ä»ħä¾ĽåıĤèĢĥ
    -0.09
    ÙĬÙĤ
    -0.09
    Ñįм
    -0.09
    éĢĶ
    -0.09
    å¤įåı¤
    -0.08
    POSITIVE LOGITS
     Wendy
    0.08
    è£Ĥ
    0.08
     Winston
    0.08
    æĬĬèĩªå·±
    0.08
    è¸ı
    0.08
    ouses
    0.07
    æĬĬèĩªå·±çļĦ
    0.07
    å°ļ书
    0.07
     exceptional
    0.07
    cation
    0.07
    Activations Density 0.001%

    No Known Activations