© 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. 22-TRANSCODER-HP
    7. 130363
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erca
    -0.27
    éĩİ
    -0.26
    åīĸ
    -0.25
    .backward
    -0.25
    屿
    -0.25
     unit
    -0.24
     exit
    -0.24
    为客æĪ·
    -0.24
     report
    -0.24
     ruth
    -0.23
    POSITIVE LOGITS
     Initiative
    0.25
     ë¬¼ë¡ł
    0.24
    åĩłä¸ªäºº
    0.24
     Хо
    0.24
    èij¡
    0.24
     Hast
    0.24
    fortune
    0.23
     gord
    0.23
    å¡«è¡¥
    0.23
    红åĪ©
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.