© 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. 12386
    Prev
    Next
    INDEX
    Explanations

    business and orders

    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
    åĿĽ
    -0.20
    çªŁ
    -0.20
    çij°
    -0.18
    èIJ¥éĢłèī¯å¥½
    -0.18
    人群ä¸Ń
    -0.18
    åIJĮå¿ĥ
    -0.18
    MLE
    -0.18
    ä¸įæİĴéĻ¤
    -0.17
     Kimber
    -0.17
    åį«è§Ĩ
    -0.17
    POSITIVE LOGITS
    æĿ¥èĩª
    0.26
    份é¢Ŀ
    0.24
    订åįķ
    0.23
    ä¾Ĩèĩª
    0.22
    æľºä¼ļ
    0.22
     orders
    0.22
    _orders
    0.21
    æĿ¥æºIJ
    0.21
     workload
    0.21
    æĿ¥
    0.20
    Activations Density 0.060%

    No Known Activations