© 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. 108559
    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
    åĬ¨éĿĻ
    -0.26
    æĸ¡
    -0.25
     Coin
    -0.25
    人çļĦ
    -0.25
     Kath
    -0.25
    иÑħ
    -0.25
    游
    -0.25
    eenth
    -0.24
     Eug
    -0.24
    ·»
    -0.24
    POSITIVE LOGITS
    /ajax
    0.31
     tolerate
    0.26
    ritel
    0.25
    ivamente
    0.24
    rition
    0.24
     mineral
    0.24
    èµĸ以çĶŁåŃĺ
    0.23
     tol
    0.23
    è¡¨æł¼
    0.23
    :bold
    0.23
    Activations Density 2.216%

    No Known Activations

    This feature has no known activations.