© 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. 8145
    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
    esis
    -0.31
    uis
    -0.27
     vw
    -0.26
    èļĢ
    -0.25
    ãĥĭ
    -0.23
    ä¸Ńåľº
    -0.23
     hail
    -0.23
    Ports
    -0.23
     directly
    -0.23
     medium
    -0.23
    POSITIVE LOGITS
    acion
    0.24
    æŃ£ç¡®
    0.24
    chest
    0.24
    请大家
    0.24
     understandably
    0.24
    循
    0.24
    åİŁæĸĩåľ°åĿĢ
    0.23
     bounced
    0.23
    çļĦæł·åŃIJ
    0.23
    .TryParse
    0.23
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.