© 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. 107783
    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
    å¼Ģ端
    -0.28
    .xhtml
    -0.26
    .ua
    -0.25
    dur
    -0.25
    .tv
    -0.24
     period
    -0.24
     millennia
    -0.23
     panel
    -0.23
    cs
    -0.23
    离å¼ĢäºĨ
    -0.23
    POSITIVE LOGITS
    å¼Ĭ
    0.29
    pires
    0.29
    thood
    0.27
    chet
    0.26
    顶
    0.25
    anye
    0.25
    inho
    0.25
    ç¢į
    0.24
    affe
    0.24
     sạn
    0.24
    Activations Density 28.503%

    No Known Activations

    This feature has no known activations.