© 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. 10702
    Prev
    Next
    INDEX
    Explanations

    football and league career

    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
    åŁİå¸Ĥ建设
    -0.19
    glas
    -0.18
    words
    -0.18
    pitch
    -0.18
    èµŀåIJĮ
    -0.17
    çļĦèĥĮåIJİ
    -0.17
    å½ĵæĹ¥
    -0.16
    äºĶå®ĺ
    -0.16
    çŀ½
    -0.16
     persons
    -0.16
    POSITIVE LOGITS
    表çİ°
    0.23
    åĸĤ
    0.19
    _dual
    0.19
    两级
    0.19
    cape
    0.19
    nj
    0.19
    表çı¾
    0.19
     ÑĥÑģп
    0.18
    æĸĻ
    0.18
    çŁ¥å·±
    0.18
    Activations Density 0.118%

    No Known Activations