© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    country names and allied forces

    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
    ç«ŀ
    -0.20
    å¸ĪèĮĥ
    -0.19
    èįĴ
    -0.19
    豪éŨ
    -0.19
    å¼ĤæĢ§
    -0.19
    åIJIJ
    -0.19
    ç»Ħå§Ķä¼ļ
    -0.19
    åľ¨çº¿
    -0.19
    tribute
    -0.18
    aul
    -0.18
    POSITIVE LOGITS
     rede
    0.22
    æĮ½
    0.21
    imary
    0.21
    bject
    0.20
    壮大
    0.19
    hood
    0.19
    人æ°ijæľįåĬ¡
    0.18
    alink
    0.18
    ourg
    0.17
    ISP
    0.17
    Activations Density 0.007%

    No Known Activations