© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 16391
    Prev
    Next
    INDEX
    Explanations

    matches, tournaments, qualify

    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
    æł¡åĮº
    -0.27
    индивид
    -0.26
    благо
    -0.23
    индив
    -0.23
    åħ¨æł¡
    -0.22
    ÑĩÑĢежден
    -0.22
     ÐĶмиÑĤÑĢ
    -0.22
    âģļ
    -0.21
    еÑģÑĤеÑģÑĤвенн
    -0.21
    ÑĩÑĢ
    -0.21
    POSITIVE LOGITS
    åIJĦåĽ½
    0.33
    æľ¬åĽ½
    0.30
     countries
    0.29
    ä¸¤åĽ½
    0.28
    æĪIJåijĺåĽ½
    0.28
    åħ¶ä»ĸåĽ½å®¶
    0.28
    countries
    0.27
     FIFA
    0.26
    åľ¨åħ¨çIJĥ
    0.25
    .country
    0.25
    Activations Density 0.056%

    No Known Activations