© 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. 10341
    Prev
    Next
    INDEX
    Explanations

    opening quotation or parenthesis

    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
    tl
    -0.20
    çĿĢå®ŀ
    -0.20
    DataContract
    -0.17
    į
    -0.17
    ä¸įä»ħåı¯ä»¥
    -0.17
    ä»»ä½ķä¸Ģ个
    -0.17
    icamente
    -0.17
    è¿ĻæŶ
    -0.17
     [/
    -0.16
    CTR
    -0.16
    POSITIVE LOGITS
    对ä¸įèµ·
    0.17
    Ãłi
    0.17
    èĦĨ
    0.17
    污
    0.17
     عÙĨÙĩا
    0.17
    社ä¼ļåĮĸ
    0.16
    çĿĽ
    0.16
    “That
    0.16
    éĤª
    0.16
    ogh
    0.16
    Activations Density 0.082%

    No Known Activations