© 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. 90337
    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
    ÑĤин
    -0.26
    .metro
    -0.25
    çĦŀ
    -0.25
     vex
    -0.25
    nce
    -0.24
     ма
    -0.24
    itel
    -0.24
    arial
    -0.24
     particularly
    -0.23
    <Map
    -0.23
    POSITIVE LOGITS
    轨
    0.31
     unp
    0.27
    éŀĺ
    0.27
    atham
    0.27
    -Cs
    0.26
    è¿ĩ渡
    0.26
    åľ¨è¿ĩæ¸¡æľŁ
    0.26
    家éķ¿ä»¬
    0.25
    åĪijèѦ
    0.25
    isers
    0.25
    Activations Density 16.008%

    No Known Activations

    This feature has no known activations.