© 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. 108689
    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
    æĪijæĬĬ
    -0.29
    MEA
    -0.26
    uids
    -0.26
    æĸ°äºº
    -0.26
    åŃ£
    -0.25
    æľĪ以æĿ¥
    -0.25
    mdb
    -0.24
    STA
    -0.24
    cest
    -0.24
    ä»ĸçŁ¥éģĵ
    -0.24
    POSITIVE LOGITS
    èĸ°
    0.26
    åļ£
    0.26
    inburgh
    0.25
    [][]
    0.25
    raf
    0.25
     çıkan
    0.25
    å¾ħ
    0.24
    çĬ¯
    0.24
    æĵį
    0.24
    andbox
    0.24
    Activations Density 48.580%

    No Known Activations

    This feature has no known activations.