© 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. 24292
    Prev
    Next
    INDEX
    Explanations

    a/an followed by noun

    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
    çªł
    -0.09
    ä¸Ńå¿ĥåŁİåĮº
    -0.08
    ACITY
    -0.08
    jour
    -0.08
    ç½²
    -0.08
    ¢åįķ
    -0.08
    èĬ±å¼Ģ
    -0.08
    umat
    -0.08
    azzi
    -0.08
    å±ħ家
    -0.08
    POSITIVE LOGITS
    èĩªæľī
    0.10
    å®ŀéªĮ室
    0.09
    å¿Ļç¢Į
    0.09
    å½±éĻ¢
    0.09
     cop
    0.09
    åĮ»åĬ¡
    0.09
    é£ŁåłĤ
    0.08
    æĹłçĸij
    0.08
    ç½¢äºĨ
    0.08
     cafe
    0.08
    Activations Density 0.089%

    No Known Activations