© 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. 13426
    Prev
    Next
    INDEX
    Explanations

    ) followed by verb or article

    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
    éĢĢåĽŀ
    -0.22
    æľīåĬ©äºİ
    -0.20
    ä½ĵçİ°åľ¨
    -0.19
    éĥ½èĥ½
    -0.19
    camp
    -0.18
    èĢĮä¸Ķ
    -0.18
    棹
    -0.18
    æľīåĪ©äºİ
    -0.18
    以便
    -0.17
    ä½ķåĨµ
    -0.17
    POSITIVE LOGITS
    ä¸Ģå°ģ
    0.21
    æĺ¯ä¸Ģ个
    0.21
    æĺ¯ä¸ĢåĢĭ
    0.20
    ä¸Ģåij³
    0.20
    æĺİ天
    0.20
    çļĦ身影
    0.19
     اÙĦÙħج
    0.18
    æĺ¯ä¸Ģ家
    0.18
    æĺ¯ä¸Ģä½į
    0.18
    ä¸Ģå¹´ä¸Ģ度
    0.18
    Activations Density 0.156%

    No Known Activations