© 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. 16579
    Prev
    Next
    INDEX
    Explanations

    Korean-sounding names ending in ong or ung

    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
    侧ç»ĵæŀĦæĢ§
    -0.17
    尽管
    -0.17
    åijĢ
    -0.17
    uting
    -0.17
    ç§įç±»
    -0.17
    èĨ
    -0.17
    侬
    -0.16
    å¨ĺå¨ĺ
    -0.16
     Closing
    -0.16
    缸è¾ĥäºİ
    -0.16
    POSITIVE LOGITS
    年人
    0.22
    anan
    0.21
    ä¸ĢåĽŀäºĭ
    0.18
    око
    0.18
    ÑĤики
    0.18
    duct
    0.17
    jit
    0.17
    seo
    0.17
    tif
    0.17
    ture
    0.17
    Activations Density 0.019%

    No Known Activations