© 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. 64671
    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
    æ³¥
    -0.26
    ¢åįķ
    -0.26
    çŃĴ
    -0.25
     indirect
    -0.25
    lein
    -0.25
    rego
    -0.25
    locked
    -0.24
    lang
    -0.24
    ç¦ģ
    -0.24
    ahoma
    -0.24
    POSITIVE LOGITS
    çļĦ第ä¸Ģ个
    0.29
    azes
    0.27
    nez
    0.27
    ä¸ŃåĽ½æĶ¿åºľ
    0.26
    ìŀĩ
    0.26
    pisa
    0.26
    phe
    0.25
    acia
    0.24
     radix
    0.24
    urred
    0.24
    Activations Density 10.067%

    No Known Activations

    This feature has no known activations.