© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7211
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人çĶŁçļĦ
    -0.28
    æĿijéķĩ
    -0.27
    æĬķèµĦé¢Ŀ
    -0.26
    é¢ĦæĸĻ
    -0.25
    说è¿ĩ
    -0.24
     achieved
    -0.23
    侦æİ¢
    -0.23
     régl
    -0.23
     japan
    -0.23
    åķĸ
    -0.23
    POSITIVE LOGITS
    å¾Ĺ好
    0.26
    adoo
    0.25
    lear
    0.25
     Aff
    0.24
     haz
    0.24
    ÙĬرا
    0.24
    (top
    0.24
    ÈĻi
    0.23
    大å°ı
    0.23
    wards
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.