© 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. 63938
    Prev
    Next
    INDEX
    Explanations

    Greek names and origin

    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
     Pac
    -0.10
    æ§Į
    -0.09
    æ´º
    -0.09
    éĤij
    -0.09
    å¥ij
    -0.09
    pac
    -0.09
    æĶ¾çľ¼
    -0.08
     Sioux
    -0.08
     arb
    -0.08
    èķ¤
    -0.08
    POSITIVE LOGITS
    å¸ĮèħĬ
    0.18
     Greek
    0.16
     Greece
    0.15
    Greek
    0.13
    å®Ļ
    0.12
    åľ°ä¸Ńæµ·
    0.12
     그리ìĬ¤
    0.12
     Greeks
    0.11
    atos
    0.11
    gree
    0.11
    Activations Density 0.096%

    No Known Activations