© 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. 59076
    Prev
    Next
    INDEX
    Explanations

    clinical trial phases or types

    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
    å¥
    -0.09
    åī©
    -0.09
    åĪ©äºİ
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    ../../../
    -0.07
    ç°ĭ
    -0.07
     tslint
    -0.07
    æİĮ
    -0.07
    NF
    -0.07
    æĹĮ
    -0.07
    POSITIVE LOGITS
    edly
    0.09
    项
    0.09
    actory
    0.09
    ä¸įåIJĮçļĦ
    0.09
    缮çļĦ
    0.09
    ovenant
    0.09
    广çĶµ
    0.09
    oven
    0.08
    大äºİ
    0.08
    åįİ缼
    0.08
    Activations Density 0.218%

    No Known Activations