© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2231
    Prev
    Next
    INDEX
    Explanations

    Labor union

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
     :";↵
    -0.24
    ++){↵↵
    -0.20
    enames
    -0.19
    ktion
    -0.19
    ámara
    -0.19
    keterangan
    -0.19
     swiper
    -0.18
     puzzle
    -0.18
     crt
    -0.18
    ampire
    -0.18
    POSITIVE LOGITS
    ç½¢
    0.38
    å·¥ä¼ļ
    0.35
    工人
    0.33
     unions
    0.32
     union
    0.31
    union
    0.29
    æĢ»å·¥ä¼ļ
    0.28
    worker
    0.26
    ç½
    0.26
    Union
    0.26
    Activations Density 0.196%

    No Known Activations