© 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. 64611
    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
    irt
    -0.28
    IRT
    -0.28
    ood
    -0.26
    æĽĿåħī
    -0.26
    PLETED
    -0.26
    zel
    -0.25
    ZIP
    -0.25
    essed
    -0.24
    wüns
    -0.24
     Gazette
    -0.24
    POSITIVE LOGITS
    åijĬè¯īä»ĸ
    0.26
     ÑħоÑĤÑĮ
    0.25
    .nan
    0.24
    秣èµģ
    0.24
     Cutting
    0.24
     Alibaba
    0.24
     Liber
    0.24
    Round
    0.24
    èĩ´åij½
    0.23
     leasing
    0.23
    Activations Density 5.447%

    No Known Activations

    This feature has no known activations.