© 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. 13357
    Prev
    Next
    INDEX
    Explanations

    latest updates and alerts

    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
    æļĤ
    -0.20
    .copyOf
    -0.20
    rij
    -0.19
    èĭŁ
    -0.19
    -lang
    -0.19
    èĮ
    -0.18
    ä¸¤å¼ł
    -0.18
    åĢĴ
    -0.18
    [href
    -0.18
    ég
    -0.17
    POSITIVE LOGITS
    æ¯ıæĹ¥
    0.22
    èİ·å¾ĹæĽ´å¤ļ
    0.21
    ç¡Ŀ
    0.20
     daily
    0.20
     news
    0.19
     sweep
    0.19
     Daily
    0.19
    æĽ´å¤ļ精彩
    0.19
    羡
    0.18
    Daily
    0.18
    Activations Density 0.012%

    No Known Activations