© 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. 140683
    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
     coup
    -0.25
     Prefer
    -0.24
     tall
    -0.24
    éĴ¤
    -0.24
     Distributed
    -0.23
    çľ¼æ³ª
    -0.23
     Colleg
    -0.23
    åĩłå¹´
    -0.23
    fans
    -0.23
    éĵ¸éĢł
    -0.23
    POSITIVE LOGITS
    orum
    0.29
     draw
    0.28
    roach
    0.27
    ith
    0.26
    说ä»Ģä¹Ī
    0.26
    åħ¥
    0.25
    ase
    0.24
    .argsort
    0.23
    æĸ¹ä¾¿
    0.23
    tract
    0.23
    Activations Density 0.574%

    No Known Activations

    This feature has no known activations.