© 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. 59402
    Prev
    Next
    INDEX
    Explanations

    man was found

    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
     khúc
    -0.09
    _grade
    -0.09
    æµ·æ£ł
    -0.09
    ä¸Ģç·Ĵ
    -0.08
     Grade
    -0.08
    ä¸Ńå°ıåѦçĶŁ
    -0.08
    uj
    -0.08
    åĹĴ
    -0.08
    ä¸Ńå°ıåŀĭ
    -0.08
    è²¼
    -0.08
    POSITIVE LOGITS
    身ä½ĵåģ¥åº·
    0.09
    红æĺŁ
    0.08
    SION
    0.08
    æĺ¨æĻļ
    0.08
    ÙĬÙĦÙĬ
    0.08
    åľ¨åħ¨åĽ½
    0.08
    ema
    0.08
    æľīä¸Ģ个
    0.08
    .Virtual
    0.08
    æĺ¨å¤©
    0.08
    Activations Density 0.191%

    No Known Activations