© 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. 29768
    Prev
    Next
    INDEX
    Explanations

    Johns Hopkins University

    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
     Lane
    -0.10
    åħ±äº§åħļåijĺ
    -0.09
    еле
    -0.09
    _lane
    -0.09
    ä¸ŃåĽ½å¸Ĥåľº
    -0.09
    èĩªæĿ¥
    -0.09
    åĮĹ约
    -0.09
    æĸ¹åľĨ
    -0.08
    DataStream
    -0.08
     вкÑĥÑģ
    -0.08
    POSITIVE LOGITS
     worst
    0.09
    sal
    0.09
    ש×ŀ
    0.08
    å°½
    0.08
    обÑĢаз
    0.08
    agram
    0.08
    èĴ¯
    0.08
    认è¯Ĩ
    0.08
    aga
    0.08
    æ¿®
    0.08
    Activations Density 0.005%

    No Known Activations