© 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. 14287
    Prev
    Next
    INDEX
    Explanations

    question markers and specific topics

    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
    Bindings
    -0.21
    è°ij
    -0.21
    ä¸İä¼Ĺä¸įåIJĮ
    -0.21
    åĿĩ使åħ¶
    -0.20
    åĢ¼å¾Ĺä¸Ģ
    -0.20
     coeffs
    -0.20
     avis
    -0.20
     rẻ
    -0.20
    åįĬ天
    -0.20
    alchemy
    -0.20
    POSITIVE LOGITS
     species
    0.21
     all
    0.21
    ä¸ĸ人
    0.20
    æķĻæĿIJ
    0.20
    krit
    0.20
    ä¸įæĸŃå¢ŀåĬł
    0.20
    çī©ç§į
    0.19
    åĬ¨çī©
    0.19
    é£ŀè·ĥ
    0.19
    çİ°ä»Ĭ
    0.19
    Activations Density 0.013%

    No Known Activations