© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15261
    Prev
    Next
    INDEX
    Explanations

    residences and units

    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
    è¿Ļ件
    -0.20
    ulp
    -0.20
    ä¸ĢæĬĬ
    -0.19
    سÙĦØ·
    -0.19
    éļĨ
    -0.19
    âĦ¡
    -0.19
    à¹Ĥรà¸ĩà¸ŀ
    -0.19
    tsky
    -0.18
    æł¸éħ¸
    -0.18
    ipop
    -0.18
    POSITIVE LOGITS
    宽æķŀ
    0.27
     rooms
    0.26
     units
    0.25
    个ä½ĵ
    0.24
    æĪ¿éĹ´
    0.24
     individual
    0.23
    æľīä¸įåIJĮçļĦ
    0.23
    åĿĩ为
    0.23
    units
    0.23
    éĴ¦
    0.23
    Activations Density 0.031%

    No Known Activations