© 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. 16428
    Prev
    Next
    INDEX
    Explanations

    award for gallantry or honour

    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
    Healthy
    -0.21
    åģ¥åº·çļĦ
    -0.21
     preg
    -0.20
    天é¹ħ
    -0.20
     оÑĢг
    -0.19
     slick
    -0.19
     projections
    -0.18
    healthy
    -0.18
    bastian
    -0.18
     advertiser
    -0.18
    POSITIVE LOGITS
    åĭĭç«ł
    0.29
    æľįå½¹
    0.27
    å¥ĸåĬ±
    0.24
    èĭ±åĭĩ
    0.23
    表彰
    0.23
     medals
    0.22
    æĻĭåįĩ
    0.22
    é¢ģåıij
    0.21
    å¥ĸ
    0.21
    åĭĭ
    0.21
    Activations Density 0.028%

    No Known Activations