© 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. 60956
    Prev
    Next
    INDEX
    Explanations

    children's health and development

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªä¸»çłĶåıij
    -0.09
    éĩıåĮĸ
    -0.09
     men
    -0.09
    é¢Ģ
    -0.09
    æĹ¥æ¸IJ
    -0.09
    åIJĮç±»
    -0.09
    èIJ½
    -0.08
    leg
    -0.08
    çķ¥
    -0.08
    å¾ĹäºĨ
    -0.08
    POSITIVE LOGITS
    äºijéĽĨ
    0.09
    _FC
    0.09
    é¹°
    0.09
    ysi
    0.09
    åIJĴ
    0.08
    åı¯ä»¥çĽ´æİ¥
    0.08
    æıŃ
    0.08
    çļĦåŃ©åŃIJ
    0.08
     Reset
    0.08
     assured
    0.08
    Activations Density 0.147%

    No Known Activations