© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12591
    Prev
    Next
    INDEX
    Explanations

    authors' names

    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
    çĥŁçģ«
    -0.19
    åł¡
    -0.18
    REATE
    -0.18
    .tar
    -0.17
    istas
    -0.17
    orny
    -0.17
    à¹Ģà¸ĸ
    -0.17
    OME
    -0.17
    åī¯ä¸»å¸Ń
    -0.17
    arring
    -0.16
    POSITIVE LOGITS
    гÑĥ
    0.21
    ä¸İä¼Ĺä¸įåIJĮ
    0.18
    æľīçĤ¹
    0.18
    åľ¨çº¿
    0.18
    åij¼åIJ¸éģĵ
    0.17
     firstname
    0.17
    è¿ĩé«ĺ
    0.17
    梦è§ģ
    0.17
    ìĦŃ
    0.17
    æľīé»ŀ
    0.17
    Activations Density 0.204%

    No Known Activations