© 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. 59311
    Prev
    Next
    INDEX
    Explanations

    synopsis or summary heading

    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
     подÑĢоб
    -0.09
    æķĿ
    -0.09
    ä¸Ģæµģ
    -0.09
    详
    -0.09
    深交
    -0.09
    pill
    -0.08
     SEAL
    -0.08
    OrDefault
    -0.08
     Gaw
    -0.08
    uffle
    -0.08
    POSITIVE LOGITS
    è¦ģçĤ¹
    0.12
    æĴ®
    0.11
    æĮĪ
    0.11
     kê
    0.11
    æ°ijæĦı
    0.10
    ä¸Ģä¸ĭ
    0.10
    æıIJçĤ¼
    0.09
    ç²¾é«ĵ
    0.09
    èĪŁ
    0.09
    æĬī
    0.09
    Activations Density 0.083%

    No Known Activations