© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142586
    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
    Negative Logits
     PROC
    -0.25
    artner
    -0.23
    å±Ĥ
    -0.23
    çĽĴ
    -0.23
     proc
    -0.23
     congr
    -0.23
    å¼ĢéĢļ
    -0.23
    Usage
    -0.23
     layer
    -0.22
     explicit
    -0.22
    POSITIVE LOGITS
    atters
    0.26
    isses
    0.25
     Majesty
    0.25
     surrounds
    0.25
     houses
    0.24
    miss
    0.24
    ä¼¼
    0.23
    決å®ļ
    0.23
    stown
    0.23
    åıĭ们
    0.23
    Activations Density 38.986%

    No Known Activations

    This feature has no known activations.