© 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. 15865
    Prev
    Next
    INDEX
    Explanations

    academic years

    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
    樵
    -0.21
    §è¡Į
    -0.21
    å½ĵæĻļ
    -0.20
    ä¸Ģåı£
    -0.19
    å½ĵ天
    -0.18
    -Sep
    -0.18
    modo
    -0.18
    åĩºå·®
    -0.18
    .Column
    -0.18
    é»Ħæĺı
    -0.18
    POSITIVE LOGITS
    ä¸īå¹´
    0.36
    åħŃå¹´
    0.35
    åĽĽå¹´
    0.32
    åįĩåѦ
    0.29
    两年
    0.28
    æ¯ķä¸ļ
    0.27
    æ¯ķä¸ļåIJİ
    0.27
    äºĶå¹´
    0.25
    åħ«å¹´
    0.24
    åľ¨æł¡
    0.23
    Activations Density 0.037%

    No Known Activations