© 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. 142773
    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
    足
    -0.27
     drill
    -0.26
     drilling
    -0.25
    á¿Ĩ
    -0.25
    BM
    -0.25
    éĴ»
    -0.25
    rench
    -0.25
     dr
    -0.24
     pic
    -0.24
     Implicit
    -0.24
    POSITIVE LOGITS
    个å¤ļ
    0.28
    åİĭ缩
    0.26
     attent
    0.25
    个æĢ§åĮĸ
    0.25
    éĥ½è¢«
    0.25
    compan
    0.24
     manhã
    0.24
    解æĶ¾
    0.23
    aginator
    0.23
    schlä
    0.23
    Activations Density 16.429%

    No Known Activations

    This feature has no known activations.