© 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. 88177
    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
    Pel
    -0.27
    mÄ±ÅŁ
    -0.27
    -viol
    -0.26
    _wc
    -0.26
    æĸ°æµªå¾®åįļ
    -0.25
     ccp
    -0.25
    æĨ§
    -0.25
    amon
    -0.25
    discover
    -0.25
     cott
    -0.24
    POSITIVE LOGITS
    è¿ĺæľī
    0.32
    éĢ¢
    0.32
    [
    0.31
    *
    0.29
     Show
    0.28
    "
    0.28
    e
    0.27
     [
    0.27
     position
    0.26
     "
    0.26
    Activations Density 5.418%

    No Known Activations

    This feature has no known activations.