© 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. 90252
    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
    enu
    -0.27
    说æĺİ
    -0.26
    encv
    -0.25
    å¾Īæ£Ĵ
    -0.24
    ViewById
    -0.24
    亲
    -0.23
    charts
    -0.23
    è´¢æĬ¥
    -0.23
    alking
    -0.23
     eleg
    -0.23
    POSITIVE LOGITS
    retch
    0.26
     Drag
    0.24
     Helping
    0.24
     qed
    0.24
    /ion
    0.24
     drag
    0.23
    æµĨ
    0.23
    é»ijé¾Ļ
    0.23
     INC
    0.23
     Intercept
    0.23
    Activations Density 10.412%

    No Known Activations

    This feature has no known activations.