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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4696
    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çī©
    -0.27
    æĸĩ
    -0.26
     Year
    -0.26
    ä¸ĭè¡Į
    -0.25
    annie
    -0.25
     interchangeable
    -0.24
    ewe
    -0.24
    (\$
    -0.24
     muster
    -0.24
    è´¨
    -0.24
    POSITIVE LOGITS
    è¸ı
    0.28
    çħ§æł·
    0.27
    iox
    0.25
    æµ¼
    0.25
    ţi
    0.25
    ä¸Ģ页
    0.25
    .Touch
    0.24
    MESS
    0.24
    æĢĢæĬ±
    0.24
    unken
    0.24
    Activations Density 0.224%

    No Known Activations

    This feature has no known activations.