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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8511
    Prev
    Next
    INDEX
    Explanations

    equation or article titles

    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
    æĪĸèĢħ说
    -0.09
    ä¸įä¹ħåīį
    -0.09
    ãģĿãģ®ãģ¾ãģ¾
    -0.09
    ä¸įä»ħå¦ĤæѤ
    -0.09
     GOODMAN
    -0.09
    ä¸İæѤ
    -0.09
    è¿Ļç§įæĥħåĨµ
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    æĪĸèĢħæĺ¯
    -0.09
    èį»
    -0.09
    POSITIVE LOGITS
    åIJİåĨį
    0.08
    è¦ģç´§
    0.07
     “[
    0.07
    markup
    0.07
    æĺ¯æĢİæł·
    0.07
    æľīæľº
    0.07
     surprising
    0.07
    éĩĩçŁ¿çŃī
    0.06
    č↵↵
    0.06
     Stunning
    0.06
    Activations Density 0.541%

    No Known Activations