© 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. 11745
    Prev
    Next
    INDEX
    Explanations

    Congress, Atlantic, American

    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
    Vir
    -0.24
    çĻ½é¢Ĩ
    -0.20
    å¾ĭ
    -0.20
    èĥĮ
    -0.19
     Vir
    -0.18
    ugin
    -0.18
    åIJĥ
    -0.18
    æľīä¸įåIJĮçļĦ
    -0.18
    ioni
    -0.18
    oter
    -0.18
    POSITIVE LOGITS
    è¿Ļ个åIJįåŃĹ
    0.20
    ãģ§ãģ¯ãģªãģı
    0.20
    è¯ķçĤ¹å·¥ä½ľ
    0.19
    ç½ķ
    0.19
     aka
    0.18
    HAND
    0.18
     instead
    0.18
    è¿Ļä¸ªåľ°åĽ¾
    0.18
    æĽ¿ä»£
    0.18
    cake
    0.17
    Activations Density 1.087%

    No Known Activations