© 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. 108789
    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
    è±ģ
    -0.28
    ÑīениÑı
    -0.27
    atical
    -0.27
     trag
    -0.27
    enity
    -0.26
     helf
    -0.25
     пÑĢаво
    -0.24
    ervations
    -0.24
    ENU
    -0.24
     zost
    -0.24
    POSITIVE LOGITS
    åŨ
    0.27
     relations
    0.26
    flush
    0.26
     Relations
    0.26
    final
    0.26
    /cgi
    0.25
    .Mutable
    0.25
    Py
    0.24
    åĴ³
    0.24
    çļĦåħ³ç³»
    0.24
    Activations Density 37.962%

    No Known Activations

    This feature has no known activations.