© 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. 90188
    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
     hit
    -0.32
     Hit
    -0.26
    模
    -0.25
    åįģåħ«æĿ¡
    -0.25
     dot
    -0.25
     strikes
    -0.25
    æ»ļ
    -0.25
    åįģåħŃæĿ¡
    -0.24
    	hit
    -0.24
    lyph
    -0.24
    POSITIVE LOGITS
     Identified
    0.27
    .':
    0.26
    omore
    0.26
    onest
    0.26
    [Unit
    0.25
    [ID
    0.25
    åħ¨åľº
    0.25
    æ¤į
    0.25
    娱
    0.25
    ished
    0.24
    Activations Density 1.970%

    No Known Activations

    This feature has no known activations.