© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8034
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¨ģ
    -0.27
    authorized
    -0.26
     authorized
    -0.26
    =========↵
    -0.25
     Dem
    -0.24
    .setItem
    -0.24
     divert
    -0.23
     Mold
    -0.23
     \"%
    -0.23
     py
    -0.23
    POSITIVE LOGITS
    尽头
    0.27
     mana
    0.26
    éĿĵ
    0.25
     CIF
    0.24
    æĬľ
    0.24
    VICE
    0.23
    å·´æĭī
    0.23
     dece
    0.23
    åIJ¸éĻĦ
    0.23
    strap
    0.23
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.