© 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. 60879
    Prev
    Next
    INDEX
    Explanations

    backed by

    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
    æŃ¤é¡¹
    -0.09
    æĭ¿åĩºæĿ¥
    -0.08
     Representatives
    -0.08
    请大家
    -0.08
    å¤ĩ
    -0.08
    Ñıн
    -0.08
    æıĸ
    -0.08
    è¿Ļæĸ¹éĿ¢
    -0.08
     ways
    -0.08
    纲
    -0.08
    POSITIVE LOGITS
    å®ŀåĬĽ
    0.11
    æĢ»èµĦ产
    0.11
    Servi
    0.09
     Vand
    0.09
    èĬĴ
    0.09
     lÆ°ng
    0.09
    è¿ĩ硬
    0.09
    .arguments
    0.09
    atrix
    0.09
    èŁ¾
    0.09
    Activations Density 0.012%

    No Known Activations