© 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. 8329
    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
    é£İæł¼
    -0.29
     style
    -0.29
     factor
    -0.29
    é¢¨æł¼
    -0.27
     styles
    -0.26
     gate
    -0.26
     Young
    -0.26
     bare
    -0.26
    ulator
    -0.26
    _guess
    -0.26
    POSITIVE LOGITS
    ä¿Ŀ管
    0.29
    没éĹ®é¢ĺ
    0.28
    æĽ´å¥½çļĦ
    0.26
    aps
    0.26
     Trib
    0.26
    }'",
    0.25
    arser
    0.25
    Library
    0.24
    ä¿Ŀ
    0.24
     cooler
    0.24
    Activations Density 0.164%

    No Known Activations

    This feature has no known activations.