© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10467
    Prev
    Next
    INDEX
    Explanations

    player's and history's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸ŃåĽ½äººæ°ij
    -0.25
    让人们
    -0.21
    人们çļĦ
    -0.20
    оÑĢа
    -0.19
    setMessage
    -0.19
     peoples
    -0.19
     retries
    -0.19
    rement
    -0.19
    .closed
    -0.19
    ä¸ĸçķĮåIJĦåľ°
    -0.19
    POSITIVE LOGITS
    æĸ°æĺ¥
    0.24
    å¤ĸåĩº
    0.23
    对å¤ĸ
    0.20
     наи
    0.20
    åŃļ
    0.19
    è²Į
    0.19
    å¤ĸæĿ¥
    0.19
     promo
    0.19
     nomin
    0.19
    å¤ĸå¥Ĺ
    0.19
    Activations Density 0.073%

    No Known Activations