© 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. 90329
    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
     moyen
    -0.28
    )sender
    -0.26
    æ¾İ
    -0.25
     vin
    -0.25
    ().'/
    -0.25
    <article
    -0.24
     correspondent
    -0.23
    BootApplication
    -0.23
    -boot
    -0.23
     pressing
    -0.23
    POSITIVE LOGITS
    åıªä¸įè¿ĩ
    0.26
    åıĮçľ¼
    0.26
    .Peek
    0.25
     jap
    0.25
    emat
    0.25
    trad
    0.25
    æ¶Ŀ
    0.25
    é¢ĦæĬ¥
    0.24
    /fr
    0.24
    åįĥä¼ı
    0.24
    Activations Density 3.821%

    No Known Activations

    This feature has no known activations.