© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    belt conveyor systems

    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
    箸
    -0.20
    adel
    -0.20
    -des
    -0.19
    æĮij
    -0.19
     pen
    -0.19
     des
    -0.19
    çŃĶ辩
    -0.19
     cell
    -0.18
    sa
    -0.18
     shot
    -0.18
    POSITIVE LOGITS
    ä¼łåĬ¨
    0.26
    ç³»ç»ŁçļĦ
    0.24
    横åIJij
    0.22
    é³Ŀ
    0.21
     Conveyor
    0.21
    工人
    0.21
     conveyor
    0.20
    æ¦ĸ
    0.20
    ç³»ç»Ł
    0.20
    槽
    0.20
    Activations Density 0.054%

    No Known Activations