© 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. 131034
    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
    åĬŁå¤«
    -0.33
    dest
    -0.30
     Urb
    -0.28
    æ»ĭ润
    -0.28
    _dest
    -0.27
    åĬŁ
    -0.27
     Gat
    -0.27
     dest
    -0.27
     Destination
    -0.26
    Dest
    -0.26
    POSITIVE LOGITS
    ucle
    0.27
    çļĦä»·æł¼
    0.26
    覺
    0.26
     Mand
    0.24
     beaut
    0.24
     Tân
    0.24
    	dialog
    0.24
     Posté
    0.23
    eton
    0.23
    åħ´å¥ĭ
    0.23
    Activations Density 5.145%

    No Known Activations

    This feature has no known activations.