© 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. 6094
    Prev
    Next
    INDEX
    Explanations

    questions or explanations following a colon

    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
    Negative Logits
    ç«ĸ
    -0.10
    çıŃ
    -0.09
    ArrayOf
    -0.09
    åĨī
    -0.09
    彤
    -0.09
    票
    -0.08
    èĴ½
    -0.08
    اÙĤ
    -0.08
     scalp
    -0.08
    èĵIJ
    -0.08
    POSITIVE LOGITS
    æŶéĻIJ
    0.10
    主é¢ĺ
    0.09
    anner
    0.09
     ÑĢем
    0.09
     GAR
    0.09
     relevance
    0.09
    çļĦ主é¢ĺ
    0.09
    åĴĮåľ°åĮº
    0.09
    絡
    0.09
    é¾Ļæ¹ĸ
    0.08
    Activations Density 0.044%

    No Known Activations