© 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. 24035
    Prev
    Next
    INDEX
    Explanations

    mainly, partly, largely, perhaps, mostly because

    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
    ä¸ĢèĪ¬äºº
    -0.09
    çļĦ人æĿ¥è¯´
    -0.09
    ä¸Ńåħ³
    -0.09
    ä¸Ģéĥ¨
    -0.08
    åıijçĶŁåľ¨
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    æ¯Ĺ
    -0.08
    éļıåIJİ
    -0.08
     escap
    -0.08
    é¾Ľ
    -0.08
    POSITIVE LOGITS
    ç²¥
    0.10
    aurus
    0.10
    å®Įç»ĵ
    0.10
    ç¢Ĺ
    0.09
    æŶåĢĻ
    0.09
    .TryParse
    0.09
    æ³ī
    0.09
    纲
    0.09
    çĶµç½ij
    0.09
    .blob
    0.09
    Activations Density 0.055%

    No Known Activations