© 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. 16763
    Prev
    Next
    INDEX
    Explanations

    about

    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
    ula
    -0.18
    thon
    -0.18
    åĨ³
    -0.18
    æĶ¯æı´
    -0.18
    ç»Ŀ对
    -0.18
    åĮ¹
    -0.17
    .btnSave
    -0.17
    åIJįæł¡
    -0.17
    ErrorHandler
    -0.17
    TH
    -0.17
    POSITIVE LOGITS
    éģ¥è¿ľ
    0.20
    éĹľæĸ¼
    0.20
     Ñģобой
    0.19
    ä¸įå¾Ĺä¸į说
    0.19
     cómo
    0.18
    çļĦ对象
    0.18
     how
    0.17
    ìĥī
    0.17
    quam
    0.17
    çľĭæ¸ħ
    0.17
    Activations Density 0.033%

    No Known Activations