© 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. 19-TRANSCODER-HP
    7. 9687
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fund
    -0.29
    ABOUT
    -0.26
    produce
    -0.26
     direct
    -0.26
    About
    -0.25
    bam
    -0.25
     -
    -0.25
    essa
    -0.25
    -level
    -0.24
     dynamics
    -0.24
    POSITIVE LOGITS
    å¿ĥæĦ¿
    0.27
    ä¸Ģé¢Ĺ
    0.26
    ä¼Ĺ
    0.26
    ãĮ¢
    0.26
    å½ĵä¹ĭ
    0.26
    å¤ĩ
    0.26
    åģļé¥Ń
    0.26
    اÙĦÙĬاباÙĨ
    0.25
    å·¥ä¸ļ
    0.25
     pang
    0.25
    Activations Density 0.146%

    No Known Activations

    This feature has no known activations.