© 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. 13645
    Prev
    Next
    INDEX
    Explanations

    am/pm time notation

    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
    jmp
    -0.19
    翳
    -0.19
    ÑģÑı
    -0.18
    濯
    -0.18
    aries
    -0.18
    æĥľ
    -0.18
    iveness
    -0.17
     impro
    -0.17
    æ°ª
    -0.17
    æ¹ľ
    -0.17
    POSITIVE LOGITS
    æŵ
    0.18
    æł¹æį®ä¸įåIJĮ
    0.17
    å·¦åı³
    0.17
    éĴĬ
    0.17
    社ä¼ļåIJĦçķĮ
    0.17
    è¿Ļä¸Ģ天
    0.16
     Beats
    0.16
     InetAddress
    0.16
    èĢĨ
    0.16
    è¯ļæĦı
    0.16
    Activations Density 0.018%

    No Known Activations