© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13964
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    iline
    -0.20
    ìłģ
    -0.20
    åįĪé¥Ń
    -0.19
    é¹ĥ
    -0.19
    æĸ¯åŁº
    -0.18
    ICES
    -0.18
    è£Ķ
    -0.18
    èĩ¾
    -0.18
    iders
    -0.18
    ÑĮе
    -0.18
    POSITIVE LOGITS
    _:*
    0.21
    建设åĴĮ
    0.19
    .Disclaimer
    0.19
    (stypy
    0.19
    ä¸įåIJĮçļĦ
    0.19
    Ø£Ùģر
    0.18
    交éĢļ
    0.18
    èįĽ
    0.18
    å¥ł
    0.18
    werp
    0.17
    Activations Density 0.120%

    No Known Activations