© 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. 64790
    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
     Brace
    -0.28
    对çŃĸ
    -0.26
    /Framework
    -0.26
     ::↵
    -0.25
    该项
    -0.25
    -upper
    -0.25
    ä¹ĸ
    -0.24
     struct
    -0.24
    airro
    -0.24
    请è¾ĵåħ¥
    -0.23
    POSITIVE LOGITS
    igraph
    0.31
    erd
    0.29
    AIL
    0.29
     slides
    0.27
    ánÃŃ
    0.27
    aur
    0.27
     pres
    0.26
    et
    0.26
    kar
    0.25
    ard
    0.24
    Activations Density 23.655%

    No Known Activations

    This feature has no known activations.