© 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. 16077
    Prev
    Next
    INDEX
    Explanations

    other [adj]

    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
    第ä¸ĢæĿ¡
    -0.25
    è´¨éĩıåĴĮ
    -0.23
    é¦ĸ
    -0.20
    ä¹Łå°±æĺ¯
    -0.20
    åį³
    -0.20
    第ä¸Ģ家
    -0.19
    emodel
    -0.19
    sheets
    -0.19
    æľĢåĪĿçļĦ
    -0.19
    è¿Ļåı¥è¯Ŀ
    -0.18
    POSITIVE LOGITS
    ucci
    0.24
     assorted
    0.21
     unnamed
    0.21
    寤
    0.20
     dear
    0.20
    бÑĭÑĤ
    0.19
    å½¢å¼ı
    0.19
     extr
    0.18
    unan
    0.18
    æĢ§å¼º
    0.18
    Activations Density 0.117%

    No Known Activations