© 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. 131165
    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
    hani
    -0.28
    UNITY
    -0.26
    fried
    -0.25
    ipur
    -0.25
    ĽĦ
    -0.25
    velope
    -0.24
    ’ll
    -0.24
     Om
    -0.24
    à¹īà¸Ńม
    -0.24
    åľ¨è¿Ļ个
    -0.24
    POSITIVE LOGITS
    iners
    0.25
    ä¾ł
    0.25
    ä¸į好
    0.24
    èIJ½åĪ°
    0.24
    -roll
    0.24
     Apache
    0.23
    dot
    0.23
    inals
    0.23
    Apache
    0.23
     apache
    0.23
    Activations Density 1.176%

    No Known Activations

    This feature has no known activations.