© 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. 20-TRANSCODER-HP
    7. 130172
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bench
    -0.34
    æľĽ
    -0.30
    addock
    -0.30
    .ForegroundColor
    -0.29
    mus
    -0.28
    utory
    -0.27
     je
    -0.26
     fodder
    -0.26
     Bench
    -0.26
    errick
    -0.26
    POSITIVE LOGITS
    ·¨
    0.27
    lov
    0.26
    (connect
    0.25
    åĶĽ
    0.25
    å¨ĺ
    0.25
    _SIGNATURE
    0.25
    è¿ŀæİ¥
    0.25
    /connect
    0.24
    actually
    0.24
    .bpm
    0.24
    Activations Density 85.737%

    No Known Activations

    This feature has no known activations.