© 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. 29620
    Prev
    Next
    INDEX
    Explanations

    yahoo.com / news / inc

    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
    çĻ½äºij
    -0.09
    æĮĪ
    -0.09
    çIJĨäºĭéķ¿
    -0.08
    é¢ĨåĨĽ
    -0.08
    æĻ°
    -0.08
    寿
    -0.08
    è¹ij
    -0.08
    æĭľè®¿
    -0.08
    壽
    -0.08
    æ»´
    -0.08
    POSITIVE LOGITS
    æIJ
    0.10
    女
    0.09
     беÑģ
    0.09
    /accounts
    0.09
    å©¿
    0.09
    åĿIJ
    0.09
     uncont
    0.09
    åģļä¸Ģ个
    0.08
    LEX
    0.08
    .gc
    0.08
    Activations Density 0.003%

    No Known Activations