© 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. 39447
    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
    ethe
    -0.26
    ishing
    -0.26
    edo
    -0.26
    ewolf
    -0.25
    pto
    -0.25
     thá»ķ
    -0.25
    å¿ĥåĬ¨
    -0.24
    IVER
    -0.24
    主æµģ
    -0.24
    è¡Įä¸ļåįıä¼ļ
    -0.24
    POSITIVE LOGITS
    imb
    0.27
    -UA
    0.26
    moment
    0.25
    éĢĶä¸Ń
    0.25
    quer
    0.25
    å°ī
    0.25
    ç¼ĵ
    0.25
     brush
    0.25
     colon
    0.24
    atter
    0.24
    Activations Density 0.092%

    No Known Activations

    This feature has no known activations.