© 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. 20-TRANSCODER-HP
    7. 64742
    Prev
    Next
    INDEX
    Explanations

    medical diagnoses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĭ¥æĤ¨
    -0.26
    循
    -0.26
    =com
    -0.25
     condi
    -0.25
     slime
    -0.24
    æł¼å°Ķ
    -0.24
    -history
    -0.23
    æĤ¨çļĦåŃ©åŃIJ
    -0.23
    è¿Ļä¹Īå¤ļ
    -0.23
    tek
    -0.23
    POSITIVE LOGITS
    æĮijæĪĺ
    0.27
    æīĩ
    0.26
     Sent
    0.26
    éĢ¼
    0.25
    notated
    0.25
     unrelated
    0.25
    åĮĸ
    0.24
    handle
    0.24
     Later
    0.23
    -handle
    0.23
    Activations Density 13.060%

    No Known Activations