© 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. 90347
    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
     trợ
    -0.27
     Abrams
    -0.26
    pios
    -0.26
    æľīéĻIJ责任
    -0.26
    ugin
    -0.26
    ordo
    -0.25
    ÄĻp
    -0.25
    ugged
    -0.25
    çĤ¹å¤ļ
    -0.24
    lyn
    -0.24
    POSITIVE LOGITS
     Bath
    0.32
    åħ¨éķĩ
    0.28
    irt
    0.28
     WELL
    0.26
    _-_
    0.26
    .asp
    0.25
    è°IJ
    0.25
    -par
    0.25
    æ³
    0.25
     occup
    0.24
    Activations Density 5.936%

    No Known Activations

    This feature has no known activations.