© 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. 142198
    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
    agi
    -0.26
    .onload
    -0.25
     oneself
    -0.25
     yourself
    -0.25
    Your
    -0.24
    ennial
    -0.24
    åIJĦåİ¿
    -0.24
    uble
    -0.24
     Yourself
    -0.24
    èĢħçļĦ
    -0.24
    POSITIVE LOGITS
     Broken
    0.27
    æĹħ游ä¸ļ
    0.26
     Tourism
    0.25
    æĪª
    0.24
    å¸ķ
    0.24
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.24
     trunc
    0.24
    è¿Ļ次
    0.24
    _seen
    0.23
    AMES
    0.23
    Activations Density 0.782%

    No Known Activations

    This feature has no known activations.