© 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. 64756
    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
    段
    -0.26
    .CG
    -0.25
    æľĿ
    -0.25
    åĬĽéĩı
    -0.25
    讯
    -0.24
    elo
    -0.24
    å¼±
    -0.24
    æľĪ以æĿ¥
    -0.24
     Bran
    -0.24
    IFO
    -0.23
    POSITIVE LOGITS
    resh
    0.24
     luáºŃn
    0.23
    quarters
    0.23
    ·æĸ°
    0.22
    .inject
    0.22
    calar
    0.22
    getProperty
    0.22
    chied
    0.22
     ìŬ
    0.22
    olum
    0.22
    Activations Density 20.965%

    No Known Activations

    This feature has no known activations.