© 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. 14-TRANSCODER-HP
    7. 41768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aley
    -0.27
    ernals
    -0.25
    erton
    -0.25
     pak
    -0.25
    主
    -0.24
     forks
    -0.23
    广éĺĶçļĦ
    -0.23
    .runners
    -0.23
     commenter
    -0.23
    ijkl
    -0.23
    POSITIVE LOGITS
    epy
    0.28
    uster
    0.26
    uctions
    0.26
    EST
    0.25
     Harvest
    0.25
    ç¬ijæĦı
    0.24
    å«ģ
    0.24
    å®ģåİ¿
    0.24
     isempty
    0.24
    æİ¥åĬĽ
    0.23
    Activations Density 2.304%

    No Known Activations

    This feature has no known activations.