© 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. 108737
    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
    ower
    -0.30
    opper
    -0.28
    -Apr
    -0.27
    èµĪ
    -0.26
    stry
    -0.26
    -Core
    -0.24
    aly
    -0.24
    angles
    -0.23
    uste
    -0.23
     typeId
    -0.23
    POSITIVE LOGITS
     forward
    0.28
    åıĪæľī
    0.26
    æĥ¯
    0.24
    ä»Ģä¹Īæł·
    0.24
    è¿ĺæľīä»Ģä¹Ī
    0.24
    对äºİæĪij们
    0.23
    urement
    0.23
    贯穿
    0.23
    æľīä¸Ģä½į
    0.23
    å®ļ
    0.22
    Activations Density 29.841%

    No Known Activations

    This feature has no known activations.