© 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. 11628
    Prev
    Next
    INDEX
    Explanations

    productivity and execution

    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
    符åIJĪæĿ¡ä»¶
    -0.23
    åĮĸ解
    -0.23
    éĢĨè¡Į
    -0.22
    spots
    -0.21
    æįĤ
    -0.21
    æīĭæ³ķ
    -0.21
    åĩºæīĭ
    -0.21
    èģĶæīĭ
    -0.20
    åħ¼
    -0.20
    åĮħ容
    -0.19
    POSITIVE LOGITS
    æķĪçİĩ
    0.37
     productivity
    0.35
     productive
    0.29
    çĶŁäº§åĬĽ
    0.28
    é«ĺæķĪ
    0.27
    ä»»åĬ¡
    0.27
    纪å¾ĭ
    0.26
    çĿ£ä¿ĥ
    0.26
    execution
    0.26
    èĩªå¾ĭ
    0.26
    Activations Density 0.097%

    No Known Activations