© 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. 129263
    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
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.27
    -last
    -0.25
    íĴĢ
    -0.25
    æĮijåīĶ
    -0.25
     ÑĦл
    -0.25
    suppress
    -0.25
    endum
    -0.24
    åħĪæĬĬ
    -0.24
    mand
    -0.24
    Traits
    -0.24
    POSITIVE LOGITS
    èĤ¡
    0.27
    ifest
    0.26
    缸åIJĮ
    0.26
    ä¸įåıĺ
    0.26
    çŃīçĿĢ
    0.25
    缸åIJĮçļĦ
    0.25
    ROT
    0.24
    ายà¸Ļ
    0.24
    å½¼
    0.24
    ecz
    0.24
    Activations Density 12.210%

    No Known Activations

    This feature has no known activations.