© 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. 14182
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by events or periods

    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
    éĿ
    -0.20
    容æĺĵ
    -0.20
     panic
    -0.19
    æĺ¯æ¯Ķè¾ĥ
    -0.19
     obs
    -0.18
    argin
    -0.18
    Disposed
    -0.18
    éĿ¡
    -0.18
    æľªç»ı
    -0.17
    è¿ĩåħ³
    -0.17
    POSITIVE LOGITS
    æļ¨
    0.24
    å¿Į
    0.21
    -old
    0.21
     Annual
    0.21
     edition
    0.20
     Scar
    0.20
    edition
    0.20
    年以æĿ¥
    0.19
    ä¸ĸçķĮ
    0.19
    年纪
    0.19
    Activations Density 0.036%

    No Known Activations