© 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. 31-TRANSCODER-HP
    7. 19170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftime
    -0.28
     Contents
    -0.27
    eworthy
    -0.26
    PackageManager
    -0.25
     ContentView
    -0.25
    огÑĢам
    -0.24
    ups
    -0.24
    .site
    -0.24
    icides
    -0.24
    nel
    -0.23
    POSITIVE LOGITS
    ç¨Ģ
    0.27
     tid
    0.26
    åIJİèĢħ
    0.26
    åģļä¸ĢäºĽ
    0.26
    è¿Ļä¸įæĺ¯
    0.25
     whichever
    0.25
    ORN
    0.25
    ãĥıãĥ¼ãĥī
    0.25
    quis
    0.25
    mare
    0.25
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.