© 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. 13146
    Prev
    Next
    INDEX
    Explanations

    became a

    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
    ä½ľä¸ºä¸Ģç§į
    -0.20
    åĮºåŁŁæĢ§
    -0.20
    addAction
    -0.19
    è¿Ļç§į
    -0.19
     Abort
    -0.19
    ä½ľä¸ºä¸Ģ个
    -0.19
    knife
    -0.19
     OCR
    -0.18
    åĴĮå°ļ
    -0.18
    åı¯ä¾Ľ
    -0.18
    POSITIVE LOGITS
    æĺ¯è°ģ
    0.28
    ä¹Łå°±æĺ¯
    0.27
    èİ«è¿ĩäºİ
    0.24
     namely
    0.24
    åĽŀæĿ¥äºĨ
    0.22
    ä¹ĭ称
    0.21
    åIJĮæĹ¶ä¹Łæĺ¯
    0.21
    åĪĨåĪ«æĺ¯
    0.20
    éĤ£å°±æĺ¯
    0.20
    ANGED
    0.19
    Activations Density 0.148%

    No Known Activations