© 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. 62717
    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
     alone
    -0.28
    çļĦéĤ£ç§į
    -0.27
    Dash
    -0.27
    弩
    -0.26
    etur
    -0.26
    æĶ¯æĮģåĬĽåº¦
    -0.25
    代çIJĨåķĨ
    -0.25
    åŃº
    -0.24
    èļĵ
    -0.24
    CN
    -0.24
    POSITIVE LOGITS
    é¢Ĩ
    0.28
     ours
    0.26
    ãģķãģĦ
    0.26
    ç»Ĩèĩ´
    0.24
     Report
    0.24
     bigot
    0.24
    åIJ¸åħ¥
    0.24
    åĨįçĶŁ
    0.24
    icits
    0.23
    _sy
    0.23
    Activations Density 0.435%

    No Known Activations

    This feature has no known activations.