© 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. 12231
    Prev
    Next
    INDEX
    Explanations

    historically or traditionally

    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
     dây
    -0.09
    AMY
    -0.09
    hips
    -0.09
    èIJĮ
    -0.09
    童年
    -0.09
    _EXTERN
    -0.09
     Thảo
    -0.08
    ÅĶ
    -0.08
    åģ¥åº·æĪIJéķ¿
    -0.08
    æĹ©æĹ©
    -0.08
    POSITIVE LOGITS
    以æĿ¥
    0.09
    æľīèī²éĩijå±ŀ
    0.09
     tense
    0.09
    ä¸Ģ缴å¤Ħäºİ
    0.09
    ä¸Ģ缴æĺ¯
    0.09
    å·²ä¹ħ
    0.08
    åľ°ä½į
    0.08
    çļĦä¸Ģ大
    0.08
    åģı
    0.08
    ä¸Ģ缴éĥ½
    0.08
    Activations Density 0.049%

    No Known Activations