© 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. 15618
    Prev
    Next
    INDEX
    Explanations

    the following noun

    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
    è¿Ļæĺ¯ä¸Ģç§į
    -0.20
    è¿ĺæĺ¯ä¼ļ
    -0.19
    è¿Ļæĺ¯
    -0.19
    ä¸į幸
    -0.18
    æѤ
    -0.18
    æĽ´å¤ļ
    -0.18
    ä¸Ģçķª
    -0.18
    ÙĤات
    -0.17
    è¿Ļå°±
    -0.17
    ä¹Łæĺ¯å¦ĤæѤ
    -0.17
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.30
     ones
    0.28
    ä½Ĩä¸įéĻIJäºİ
    0.25
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.20
    使æĪij
    0.20
    让æ¶Īè´¹èĢħ
    0.19
    éĴĪ对
    0.18
    ä¸Ģ个æĺ¯
    0.18
     dreaded
    0.18
    ones
    0.18
    Activations Density 0.155%

    No Known Activations