© 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. 15811
    Prev
    Next
    INDEX
    Explanations

    enron.com

    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
    åįķä¸Ģ
    -0.20
    еÑģÑĮ
    -0.20
    grid
    -0.19
     fe
    -0.19
    ening
    -0.19
    elman
    -0.19
    çħ§é¡¾
    -0.19
     statewide
    -0.18
    åħ¨çľģ
    -0.18
    shake
    -0.18
    POSITIVE LOGITS
    è´¢æĬ¥
    0.20
    çĴŀ
    0.20
    FER
    0.20
    山顶
    0.19
    éķ¿éķ¿
    0.19
    cargo
    0.19
    ç¬ijèĦ¸
    0.19
    好转
    0.19
    ä¹°åįĸ
    0.18
     ÑģÑĦ
    0.18
    Activations Density 0.012%

    No Known Activations