© 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. 141648
    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
    æŁ¥çľĭ详æĥħ
    -0.28
    elan
    -0.28
    expect
    -0.27
    æĿĤ
    -0.27
    uter
    -0.26
    çİ°æľī
    -0.25
    Curr
    -0.25
    <tbody
    -0.25
    æīĵ好
    -0.24
    enko
    -0.24
    POSITIVE LOGITS
     mej
    0.26
    MX
    0.25
    .mx
    0.25
    صب
    0.24
     obsessed
    0.24
     morb
    0.24
    dux
    0.23
     Advantage
    0.23
    ÙĨÙī
    0.23
    ä¸Ģ次
    0.23
    Activations Density 0.150%

    No Known Activations

    This feature has no known activations.