© 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. 12871
    Prev
    Next
    INDEX
    Explanations

    during operation, drilling, game, process, exposure, production, therapy

    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
    çİ°åľ¨å·²ç»ı
    -0.23
    çİ°åľ¨çļĦ
    -0.23
    etag
    -0.22
    ä»Ĭ天
    -0.21
    缮åīįå·²ç»ı
    -0.21
    æĪij们çİ°åľ¨
    -0.20
    ä»Ĭ天æĪij们
    -0.20
     ÑģегоднÑı
    -0.20
    åľ¨åĨħçļĦ
    -0.20
    è¡°
    -0.19
    POSITIVE LOGITS
    æľŁéĹ´
    0.41
    è¿ĩç¨ĭä¸Ń
    0.38
    æľŁéĸĵ
    0.30
     ÙĪبعد
    0.30
    è¿ĩç¨ĭå½ĵä¸Ń
    0.27
    éģİç¨ĭä¸Ń
    0.26
    ç»ĵæĿŁåIJİ
    0.25
    çļĦè¿ĩç¨ĭä¸Ń
    0.24
    æľŁåĨħ
    0.23
    çļĦä¸ĢäºĽ
    0.23
    Activations Density 0.268%

    No Known Activations