© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    professional sports leagues and scouting

    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
    乡
    -0.22
    æŃ¤æ¬¡æ´»åĬ¨
    -0.21
    åħ¼
    -0.20
    SOR
    -0.19
    åħ¨åİ¿
    -0.19
    æĿijéķĩ
    -0.19
    乡æĿij
    -0.18
    è´Łè½½
    -0.18
    æľ¬æ¬¡æ´»åĬ¨
    -0.18
    ERING
    -0.18
    POSITIVE LOGITS
    èģĮä¸ļçĶŁæ¶¯
    0.20
    æĪIJ为ä¸ĢåIJį
    0.20
    /legal
    0.20
    å®ŀæĪĺ
    0.20
    çĶŁæ¶¯
    0.19
     career
    0.19
    pedia
    0.18
    è¡®
    0.18
    tas
    0.18
    æĹ¥æĬ¥
    0.18
    Activations Density 0.024%

    No Known Activations