© 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. 62809
    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
     manh
    -0.27
     boundaries
    -0.25
    çĥĪ
    -0.24
    æĬ¬èµ·å¤´
    -0.24
    ä¸ĭæĿ¥çļĦ
    -0.24
    å±ĭ顶
    -0.24
     Bound
    -0.23
    -parser
    -0.23
    etal
    -0.23
    æİīèIJ½
    -0.23
    POSITIVE LOGITS
    raig
    0.27
    åĨĮ
    0.24
    ump
    0.24
    èĩªèIJ¥
    0.24
    ALA
    0.23
    æ¿ŀ
    0.23
    æ»ĺ
    0.23
    scroll
    0.23
    åĥ®
    0.23
     Illustrated
    0.23
    Activations Density 3.145%

    No Known Activations

    This feature has no known activations.