© 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. 142036
    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
     sorry
    -0.26
     Disclaimer
    -0.25
    FLASH
    -0.24
     cooker
    -0.24
    lez
    -0.24
    rowning
    -0.23
    åħ°èĬ±
    -0.23
    Sorry
    -0.23
    erno
    -0.23
     onCancel
    -0.22
    POSITIVE LOGITS
    airport
    0.26
    é¢ľåĢ¼
    0.25
    bes
    0.24
    窦
    0.24
     Dunk
    0.24
    tain
    0.23
    Ģìŀ¥
    0.23
    çĹħ
    0.23
    åħ¨ä½ĵ
    0.23
    .FindElement
    0.23
    Activations Density 7.042%

    No Known Activations

    This feature has no known activations.