© 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. 10527
    Prev
    Next
    INDEX
    Explanations

    New England, County, boroughs

    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
    åĺ±
    -0.20
    ÑĢÑĥ
    -0.20
    urf
    -0.19
    ÑģÑĤÑĭ
    -0.19
    atters
    -0.18
     Ferrari
    -0.18
    寸
    -0.18
    马æĿ¥
    -0.17
    ees
    -0.17
    (factor
    -0.17
    POSITIVE LOGITS
    åľ°åĮºçļĦ
    0.42
    å·ŀ
    0.42
    åľ°åĮº
    0.38
    å·ŀå¸Ĥ
    0.36
     County
    0.35
    å±±åİ¿
    0.34
    åł¡
    0.32
    åİ¿
    0.32
    åľ°åįĢ
    0.31
    å·ŀåĮº
    0.31
    Activations Density 0.685%

    No Known Activations