© 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. 12248
    Prev
    Next
    INDEX
    Explanations

    duration or length of time

    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
    åĪ©çĶ¨çİĩ
    -0.20
    çĶ¨èĩªå·±çļĦ
    -0.19
    建档
    -0.19
    认è¯ĨåĪ°
    -0.18
    idon
    -0.18
    å°Ĩèĩªå·±çļĦ
    -0.17
    åİŁæĿ¥
    -0.17
    .Focus
    -0.17
    ä¹ĭéģĵ
    -0.17
     Ñģвоем
    -0.17
    POSITIVE LOGITS
     lasted
    0.28
    å¾Īéķ¿
    0.27
    åİĨæŶ
    0.26
     duration
    0.25
    贯穿
    0.24
    跨度
    0.24
    ä¸įæŃ¢
    0.23
     lasting
    0.23
    延ç»Ń
    0.23
     Duration
    0.22
    Activations Density 0.046%

    No Known Activations