© 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. 24219
    Prev
    Next
    INDEX
    Explanations

    locations and places

    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
    å±±æĿij
    -0.10
    åºĦåĽŃ
    -0.10
    æĿijéķĩ
    -0.09
    yard
    -0.09
    åIJĦåİ¿
    -0.09
    ç»ıå¼ĢåĮº
    -0.09
    åĽºå®ļçļĦ
    -0.09
    åĿŀ
    -0.09
    æ¹ĸæ³Ĭ
    -0.09
     Douglas
    -0.08
    POSITIVE LOGITS
     ÑģобÑĢан
    0.09
     din
    0.09
    ä¸ĬçıŃ
    0.09
    大è¡Ĺ
    0.09
    ä¸į足以
    0.09
    éĹ¹
    0.08
    æİĴéĺŁ
    0.08
    è¡®
    0.08
    uels
    0.08
     ÑģобиÑĢа
    0.08
    Activations Density 0.074%

    No Known Activations