© 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. 88296
    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
     stump
    -0.29
    ãģĦãģ£ãģŁ
    -0.25
    _suite
    -0.24
    æĹħ游èµĦæºIJ
    -0.24
    精彩çļĦ
    -0.24
    å¾ĩ
    -0.23
    .factor
    -0.23
    à¸Ļà¸Ńà¸ģ
    -0.23
    η
    -0.23
    èģĶ
    -0.23
    POSITIVE LOGITS
    spb
    0.28
    /layouts
    0.27
    arine
    0.27
    "https
    0.27
    irector
    0.26
    ELLOW
    0.25
    SPELL
    0.25
    lla
    0.25
    /simple
    0.24
    ottes
    0.24
    Activations Density 2.066%

    No Known Activations

    This feature has no known activations.