© 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. 142653
    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
    irie
    -0.25
    è¯Ń
    -0.25
     legs
    -0.25
     eslint
    -0.24
     account
    -0.24
     Pale
    -0.24
     Et
    -0.24
     bond
    -0.24
    Margin
    -0.24
     má»ĩnh
    -0.23
    POSITIVE LOGITS
    üss
    0.28
    éĿ
    0.27
    æ°ij主åħļ
    0.26
    èĥ¡åIJĮ
    0.26
    tors
    0.26
    ANNEL
    0.25
    æ²®
    0.25
    èĢķèĢĺ
    0.25
    çŃ²
    0.25
    éľ°
    0.25
    Activations Density 5.193%

    No Known Activations

    This feature has no known activations.