© 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. 29784
    Prev
    Next
    INDEX
    Explanations

    if you did not receive

    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
    æѤæŶ
    -0.10
    eper
    -0.09
    [sizeof
    -0.09
    Ñıд
    -0.08
    å°Ĩåľ¨
    -0.08
    nal
    -0.08
     currently
    -0.08
    /dataTables
    -0.08
     når
    -0.08
    æĸ°å¼Ģ
    -0.08
    POSITIVE LOGITS
     originally
    0.14
     yesterday
    0.14
     recently
    0.14
    æĺ¨æĹ¥
    0.14
    /is
    0.12
     ÑĢанее
    0.12
    ä¸Ģ度
    0.11
    åݻ年
    0.11
     earlier
    0.11
    otes
    0.11
    Activations Density 2.513%

    No Known Activations