© 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. 142637
    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
    ordo
    -0.27
    LOW
    -0.27
    vos
    -0.27
    LOY
    -0.25
    /trans
    -0.25
     Revel
    -0.24
     trans
    -0.24
    æĭīå¼Ģ
    -0.24
    udu
    -0.24
    ega
    -0.23
    POSITIVE LOGITS
    幡
    0.27
    ä¸Ńéĵģ
    0.26
     gunfire
    0.26
    æİ¥åĪ°
    0.26
    raft
    0.25
    ä»Ģä¹ĪåİŁåĽł
    0.25
    çľģæķĻèĤ²
    0.25
    ç«
    0.25
    ä¸Ģ群
    0.24
    oft
    0.24
    Activations Density 35.218%

    No Known Activations

    This feature has no known activations.