© 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. 62658
    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
    ugi
    -0.28
    åĪ®
    -0.28
    Tpl
    -0.27
     desn
    -0.26
    管çIJĨä¸Ńå¿ĥ
    -0.25
    ExecutionContext
    -0.25
     пÑĢиÑĩ
    -0.24
    èĪ·
    -0.24
    æ·±åĪ»
    -0.24
    .pull
    -0.24
    POSITIVE LOGITS
     bunk
    0.24
    ç»į
    0.24
    تÙĪا
    0.24
    /testing
    0.23
    é»Ħ
    0.23
    æ°ĹãģĮ
    0.23
    çħĮ
    0.23
     Objects
    0.23
    ë°ĺ
    0.23
     via
    0.22
    Activations Density 96.283%

    No Known Activations

    This feature has no known activations.