© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140975
    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
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨äºİ
    -0.26
     Äijá»Ŀi
    -0.25
    trade
    -0.25
    unix
    -0.24
    ulates
    -0.24
    à¸Ļา
    -0.24
    ↵			↵
    -0.24
    leton
    -0.24
    .desktop
    -0.23
    luet
    -0.23
    POSITIVE LOGITS
    parsed
    0.29
     ApplicationRecord
    0.25
    è¿Ļé¦ĸæŃĮ
    0.25
     ана
    0.25
    (track
    0.24
     await
    0.24
     unset
    0.24
    await
    0.24
    轨
    0.23
    姥
    0.23
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.