© 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. 10429
    Prev
    Next
    INDEX
    Explanations

    scores and numbers

    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
    诸å¦Ĥ
    -0.19
    å¥ī
    -0.18
    ä»İå°ı
    -0.18
    åĢĻ
    -0.17
    æ²ĥ
    -0.17
    ä¸İ
    -0.17
    å¹¿æ³ĽçļĦ
    -0.17
     Went
    -0.17
    .enumer
    -0.17
    æĪIJåĬŁçİĩ
    -0.17
    POSITIVE LOGITS
    ifter
    0.20
    umbo
    0.20
    евÑĭÑħ
    0.19
    жи
    0.17
    gings
    0.17
    veau
    0.17
     lance
    0.17
    åı¹æģ¯
    0.17
    èµĽåľº
    0.17
    ética
    0.17
    Activations Density 0.004%

    No Known Activations