© 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. 59465
    Prev
    Next
    INDEX
    Explanations

    gratitude to all

    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
    peg
    -0.10
    åıªè¦ģ
    -0.10
    PEG
    -0.10
     Edmund
    -0.09
     Dil
    -0.09
    鸷
    -0.09
    mac
    -0.08
    mitt
    -0.08
    gef
    -0.08
    digit
    -0.08
    POSITIVE LOGITS
    åĮ»ç§ij
    0.11
     ways
    0.09
    麽
    0.09
    illion
    0.09
    天涯
    0.09
    oro
    0.09
    çļĦæĸ¹å¼ıæĿ¥
    0.09
    0.09
    æ°¸ä¸į
    0.09
    åİĨæĿ¥
    0.09
    Activations Density 0.014%

    No Known Activations