© 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. 59098
    Prev
    Next
    INDEX
    Explanations

    newspaper names and news outlets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Fen
    -0.09
    .mar
    -0.09
    çļ´
    -0.09
    åĬłçıŃ
    -0.08
    outh
    -0.08
    éĥ¨éķ¿
    -0.08
    åIJĮä¸ļ
    -0.08
     Homes
    -0.08
    ibus
    -0.08
     restless
    -0.08
    POSITIVE LOGITS
    æĬ¥çº¸
    0.17
     newspaper
    0.16
     newspapers
    0.14
     Newspaper
    0.13
    æĬ¥è®°èĢħ
    0.10
     Daily
    0.10
     newsp
    0.10
    æĬ¥ä¸ļ
    0.10
    æŶæĬ¥
    0.10
    æĻļæĬ¥
    0.10
    Activations Density 0.156%

    No Known Activations