© 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. 11402
    Prev
    Next
    INDEX
    Explanations

    this Japanese word or phrase

    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
    ugin
    -0.20
    举ä¾ĭ
    -0.20
    èĬİ
    -0.20
     rÃłng
    -0.19
    ATAR
    -0.19
    á»ĩm
    -0.19
    eros
    -0.19
     Kardashian
    -0.19
    è°Ĵ
    -0.18
     plan
    -0.18
    POSITIVE LOGITS
    æĿ¥èĩª
    0.24
    åķĨæľº
    0.23
    èµĦæĸĻ
    0.22
    ä¾Ĩèĩª
    0.22
    åıijçĶŁåľ¨
    0.22
    çķĢ
    0.21
    æģ¸
    0.21
    çĸ¯
    0.20
    æĿ¥èĩªäºİ
    0.20
    æķ´çIJĨ
    0.20
    Activations Density 0.066%

    No Known Activations