© 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. 129012
    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
     Emp
    -0.27
     empirical
    -0.27
    autoload
    -0.27
    é¾
    -0.26
    è´Ŀ
    -0.26
     sui
    -0.25
    é¾Ł
    -0.24
    å®ŀéªĮ室
    -0.24
     empir
    -0.24
    çļĵ
    -0.24
    POSITIVE LOGITS
    erb
    0.29
    isos
    0.25
    rado
    0.24
    ç«Łæĺ¯
    0.24
    andal
    0.24
    ersen
    0.24
    stance
    0.24
    commission
    0.24
    isión
    0.24
    eric
    0.23
    Activations Density 1.219%

    No Known Activations

    This feature has no known activations.