© 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. 129244
    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
    udio
    -0.28
     fork
    -0.27
    æľĢé«ĺ
    -0.27
    cks
    -0.27
    kers
    -0.26
    Bars
    -0.25
    cers
    -0.25
    她说
    -0.25
    bars
    -0.24
    cer
    -0.24
    POSITIVE LOGITS
    ä¹Łæĺ¯å¾Ī
    0.29
     OnTriggerEnter
    0.25
    æµ·å²Ľ
    0.25
    /native
    0.25
    \base
    0.24
     ########.
    0.23
    é»Ķ
    0.23
    æĺ¯ä»Ģä¹Ī
    0.23
     eligibility
    0.23
    .wall
    0.23
    Activations Density 4.378%

    No Known Activations

    This feature has no known activations.