© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30355
    Prev
    Next
    INDEX
    Explanations

    trade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     trade
    -0.41
    è´¸æĺĵ
    -0.38
     trading
    -0.37
    交æĺĵ
    -0.33
     TRADE
    -0.33
     Trade
    -0.33
    Trade
    -0.33
     merchandise
    -0.32
     Trading
    -0.31
    åķĨåĬ¡éĥ¨
    -0.30
    POSITIVE LOGITS
    ä¸įåĪĨ
    0.27
    åij±
    0.25
    LEE
    0.25
    orphism
    0.25
    ardo
    0.24
    ìĦĿ
    0.24
    çıī
    0.23
     tuá»ķi
    0.23
    åĵģæł¼
    0.23
    Separator
    0.23
    Activations Density 1.120%

    No Known Activations