© 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. 14095
    Prev
    Next
    INDEX
    Explanations

    weight divisions

    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
    okit
    -0.21
    ä»İæł¹æľ¬ä¸Ĭ
    -0.19
    èĢ³
    -0.18
    åIJ¬è¯´
    -0.18
    缮
    -0.17
    ç§ģ
    -0.17
    ç»Ĩ
    -0.17
     tracing
    -0.16
    æĿIJæĸĻ
    -0.16
     Gand
    -0.16
    POSITIVE LOGITS
    ikel
    0.22
    çļĦçĶ·äºº
    0.21
    èĥª
    0.21
    第äºĮ大
    0.20
    帥
    0.20
    ç´ļ
    0.19
    alogy
    0.19
    级
    0.19
    éķĽ
    0.19
     Lama
    0.19
    Activations Density 0.002%

    No Known Activations