© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130177
    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
    Not in Any Lists

    No Comments

    Negative Logits
    agne
    -0.27
     cert
    -0.27
    æĢģ度
    -0.27
    enville
    -0.26
    disposing
    -0.24
    çīł
    -0.24
    æĬĽ
    -0.24
    Plot
    -0.24
    lettes
    -0.23
    dog
    -0.23
    POSITIVE LOGITS
    anzi
    0.28
    é¦ĸè¦ģ
    0.27
    è¾
    0.25
    aine
    0.24
    Found
    0.23
     Bust
    0.23
    褶
    0.23
    æĶ¶éĽĨ
    0.23
     Sands
    0.23
    æľīä¸Ģ
    0.23
    Activations Density 25.118%

    No Known Activations

    This feature has no known activations.