© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22441
    Prev
    Next
    INDEX
    Explanations

    graduation and academic terms

    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
    å¾ģ
    -0.10
    obook
    -0.09
    åĻ¨æĿIJ
    -0.09
    íħIJ
    -0.09
    åij¨åĪĬ
    -0.09
    éĴĪ
    -0.08
    æݪæĸ½
    -0.08
    让大家
    -0.08
    å¾ģéĽĨ
    -0.08
    è¯Ł
    -0.08
    POSITIVE LOGITS
     graduation
    0.16
    æ¯ķä¸ļ
    0.15
    æ¯ķä¸ļçĶŁ
    0.14
     вÑĭпÑĥÑģк
    0.13
     gradu
    0.13
     graduates
    0.12
    大åѦæ¯ķä¸ļ
    0.12
    çķ¢æ¥Ń
    0.11
    仪å¼ı
    0.11
    æİĪäºĪ
    0.10
    Activations Density 0.091%

    No Known Activations