© 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. 47602
    Prev
    Next
    INDEX
    Explanations

    celebrity names

    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
    ذر
    -0.10
    ниÑĩ
    -0.09
    è¿ĻæĶ¯
    -0.09
    èĬĿ麻
    -0.09
    åIJĿ
    -0.09
    æĬ¤æłı
    -0.09
    æ±ĩæĬ¥
    -0.09
    ÑĢÑĥÑģ
    -0.08
    åĪ©çĽĬ
    -0.08
    stra
    -0.08
    POSITIVE LOGITS
    agger
    0.10
    Lat
    0.10
    丰å¯Į
    0.09
    idas
    0.08
    _lat
    0.08
    åijĺ
    0.08
    TU
    0.08
     lat
    0.08
    emory
    0.08
    lat
    0.08
    Activations Density 0.003%

    No Known Activations