© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    God, world, serve, man

    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
    ç³ĸ
    -0.19
    纸ä¸Ĭ
    -0.19
    ess
    -0.18
    æľ¬é¢Ĩ
    -0.18
    éª
    -0.18
    渡
    -0.18
    ä¸įéĢļ
    -0.18
    .factory
    -0.18
    轿车
    -0.18
    abis
    -0.18
    POSITIVE LOGITS
    ilib
    0.20
    PACK
    0.18
     santa
    0.18
    è¹Ń
    0.17
    ä¿Ł
    0.17
    stor
    0.17
    feeding
    0.17
    åĮħè£ħ
    0.17
    æĬ¥éģĵ
    0.17
    lyph
    0.17
    Activations Density 0.148%

    No Known Activations