© 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. 129121
    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
    ictory
    -0.32
    VED
    -0.28
     bey
    -0.26
    èı¡
    -0.26
     ras
    -0.24
    psc
    -0.24
    èĽ¾
    -0.24
     decltype
    -0.24
    cene
    -0.23
    wayne
    -0.23
    POSITIVE LOGITS
    å®īæİĴ
    0.25
    å¥ĭæĸĹ缮æłĩ
    0.25
    ASY
    0.24
     ?
    0.24
    å¾Ħ
    0.24
    大å°ı
    0.23
    çļĦæĦŁè§ī
    0.23
     comparable
    0.23
    down
    0.23
    ç²®
    0.23
    Activations Density 1.698%

    No Known Activations

    This feature has no known activations.