© 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. 129007
    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
    isable
    -0.30
    eming
    -0.27
     buckle
    -0.26
    篪
    -0.26
    足
    -0.25
    æľįåĬ¡æľºæŀĦ
    -0.24
    ий
    -0.24
    fab
    -0.24
    izador
    -0.24
    ãģ»ãģĭ
    -0.24
    POSITIVE LOGITS
    ola
    0.28
    łĢ
    0.27
    èĥ¼
    0.24
    æĸĩåĮĸä¼łæĴŃ
    0.24
    ç»ĵçŁ³
    0.24
    _VISIBLE
    0.24
    è´¦
    0.24
    POSIT
    0.24
    ole
    0.24
    ">#
    0.24
    Activations Density 83.669%

    No Known Activations

    This feature has no known activations.