© 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. 13208
    Prev
    Next
    INDEX
    Explanations

    industrial facilities and operations

    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
    ä½ľä¸ºä¸ĢåIJį
    -0.20
    佩æĪ´
    -0.20
     buckle
    -0.20
     Lounge
    -0.19
    éķħ
    -0.19
    ä¼ļ议精ç¥ŀ
    -0.19
    éķ±
    -0.19
    ÑĪив
    -0.19
    éĶĩ
    -0.19
    交éĻħ
    -0.19
    POSITIVE LOGITS
    æĬķ产
    0.39
    设æĸ½
    0.34
    çĶŁäº§çļĦ
    0.31
    åİĤæĪ¿
    0.31
    åİĤ
    0.30
    产èĥ½
    0.30
    ä¸ĭ游
    0.30
    çĶŁäº§
    0.30
    å·¥åİĤ
    0.29
    çĶŁäº§èĥ½åĬĽ
    0.28
    Activations Density 0.087%

    No Known Activations