© 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. 18-TRANSCODER-HP
    7. 88338
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åijĹ
    -0.29
    çĽĶ
    -0.24
     TEM
    -0.24
     Mein
    -0.24
    è´¢æĬ¥
    -0.24
    ade
    -0.23
    ÙĪÙħ
    -0.23
    ä¼ijæģ¯
    -0.23
    ë¥ĺ
    -0.23
     Male
    -0.23
    POSITIVE LOGITS
    bserv
    0.28
    nnen
    0.24
    .raises
    0.24
     bet
    0.24
    .addObject
    0.24
     susceptible
    0.24
     marketers
    0.23
    å¼ij
    0.23
     letters
    0.23
     scratched
    0.23
    Activations Density 4.809%

    No Known Activations

    This feature has no known activations.