© 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. 8481
    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
    raphic
    -0.28
    çݦ
    -0.26
    BI
    -0.26
    yth
    -0.26
    /gtest
    -0.26
    arsity
    -0.26
    BuilderFactory
    -0.25
    Writable
    -0.24
    declare
    -0.24
     utilities
    -0.24
    POSITIVE LOGITS
    åĮºåĨħ
    0.31
    沪
    0.31
    大éĻĨ
    0.29
    åħľ
    0.27
     straps
    0.27
     strap
    0.26
    ingly
    0.26
    wards
    0.26
     amb
    0.25
    æĸ°åŀĭ
    0.25
    Activations Density 0.311%

    No Known Activations

    This feature has no known activations.