© 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. 15859
    Prev
    Next
    INDEX
    Explanations

    will support effort continue

    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
    ç«
    -0.23
    æĪIJäºĨ
    -0.21
    ç´§å¼ł
    -0.20
    è§īéĨĴ
    -0.20
    ç»ıéªĮ丰å¯Į
    -0.19
    åIJĦæľī
    -0.19
    æĤĦ
    -0.19
    åı·
    -0.19
    转æĬĺ
    -0.19
    å°ıå°ı
    -0.19
    POSITIVE LOGITS
    ç»Ŀä¸į
    0.37
    å°Ĩ继ç»Ń
    0.32
    åĨ³ä¸į
    0.29
    çļĦåĨ³å¿ĥ
    0.26
    å°ĨæĮģç»Ń
    0.25
    èĩ´åĬĽäºİ
    0.23
    å§ĭç»ĪåĿļæĮģ
    0.23
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.23
    ä¸įè´Ł
    0.23
    ç»Ŀ对ä¸įä¼ļ
    0.23
    Activations Density 0.054%

    No Known Activations