© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    sprint, agility, or test

    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
    麻å°Ĩ
    -0.21
    dì
    -0.21
    æŀķ头
    -0.20
    ç¾Ĭæ¯Ľ
    -0.20
    æĦŁäºº
    -0.20
    èĦĸåŃIJ
    -0.20
    itarian
    -0.19
    lose
    -0.19
    лав
    -0.19
    èĪĴ
    -0.19
    POSITIVE LOGITS
     sprint
    0.21
    çļĦä¸ĢåĪĩ
    0.20
     Tasks
    0.19
    apg
    0.19
    Awesome
    0.19
    ç²¾é«ĵ
    0.18
    guns
    0.18
    metrics
    0.18
     synerg
    0.18
     quarterback
    0.18
    Activations Density 0.014%

    No Known Activations