© 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. 24019
    Prev
    Next
    INDEX
    Explanations

    graduated with honors or degree

    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
    uch
    -0.09
     пÑĢог
    -0.09
    urst
    -0.09
    atty
    -0.08
    éĢļ讯
    -0.08
    UCH
    -0.08
     McCartney
    -0.08
    家åĬ¡
    -0.08
    è¿ĽæŃ¥
    -0.08
    .addSubview
    -0.08
    POSITIVE LOGITS
    è¯Ŀ说
    0.10
    æ¶Īæģ¯ç§°
    0.09
    满满çļĦ
    0.09
    Breadcrumb
    0.09
    å¿IJ
    0.09
    åħ¶
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    loh
    0.09
    ä¸ĩ亿
    0.09
    å¾Īä½İ
    0.08
    Activations Density 0.076%

    No Known Activations