© 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. 11934
    Prev
    Next
    INDEX
    Explanations

    indoor track and field championships

    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
    纡
    -0.22
     duyá»ĩt
    -0.20
    поÑĤ
    -0.19
    UNCH
    -0.19
     Barnett
    -0.19
    план
    -0.19
     заÑĤ
    -0.19
     ожида
    -0.19
    æĢĿ绪
    -0.18
    _Normal
    -0.18
    POSITIVE LOGITS
    å½¢å¼ı
    0.22
    asil
    0.21
     Hass
    0.21
    estyle
    0.20
    itational
    0.20
    表æ¼Ķ
    0.20
    ä¸ĸçķĮçļĦ
    0.19
    大ä¼ļä¸Ĭ
    0.19
    æļ¨
    0.19
    uin
    0.19
    Activations Density 0.041%

    No Known Activations