© 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. 88286
    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
    asts
    -0.27
    itz
    -0.27
    ç¿ĺ
    -0.26
     Richie
    -0.25
    foods
    -0.25
     Masters
    -0.25
    éĵģ
    -0.24
    طا
    -0.24
    à¸IJ
    -0.24
     Rem
    -0.24
    POSITIVE LOGITS
     fire
    0.29
    fire
    0.28
    æĶ¯æĮģåĬĽåº¦
    0.27
    omi
    0.25
    .forName
    0.24
     wrappers
    0.24
    表æ¼Ķ
    0.24
    ä»ĸ对
    0.23
    fund
    0.23
    Vtbl
    0.23
    Activations Density 0.199%

    No Known Activations

    This feature has no known activations.