© 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. 20-TRANSCODER-HP
    7. 64880
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    umar
    -0.31
    apore
    -0.28
    OSH
    -0.27
    errick
    -0.26
     Ritual
    -0.25
    aber
    -0.25
    缺
    -0.25
     Magn
    -0.25
    ¾ç¤º
    -0.24
    æĮĸ
    -0.24
    POSITIVE LOGITS
     recal
    0.32
    -controls
    0.27
    -mask
    0.26
    åĪ°æŶåĢĻ
    0.26
     rebounds
    0.26
    åIJĦçľģ
    0.25
    arians
    0.25
     bak
    0.25
    -rel
    0.25
    	cal
    0.25
    Activations Density 3.116%

    No Known Activations

    This feature has no known activations.