© 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. 11386
    Prev
    Next
    INDEX
    Explanations

    place names ending in "-el", "-ow", "-u", "-ove", "-eth", "-ans", "-ar", "-od", "-ane", "-aw"

    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
    é¢ļ
    -0.20
    League
    -0.20
    形象
    -0.19
    èĻ±
    -0.19
    .react
    -0.19
    åľ¨å¹¿å·ŀ
    -0.18
    ì²Ń
    -0.18
    èīĺ
    -0.18
    league
    -0.18
    æĮĩå°ĸ
    -0.18
    POSITIVE LOGITS
    ä¸Ģ缴åĪ°
    0.23
    ä¸Ģ大
    0.21
    缴èĩ³
    0.20
    åı¤ä»Ĭ
    0.19
     Baba
    0.19
    æĸ¹åIJij
    0.19
    çľĭ好
    0.19
    ç½ijåĿĢ
    0.18
    ä¸Ģå°ı
    0.18
    临è¿ij
    0.18
    Activations Density 0.142%

    No Known Activations