© 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. 6490
    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
    鼷
    -0.26
    vant
    -0.26
     desn
    -0.26
     hust
    -0.25
    æĹ¢
    -0.24
     Stern
    -0.24
    OOM
    -0.24
     Mint
    -0.24
     GPL
    -0.24
    Stick
    -0.23
    POSITIVE LOGITS
    uhan
    0.28
    ä¸īæľŁ
    0.27
    -functional
    0.27
    hma
    0.26
    strand
    0.26
    UND
    0.26
    æĸ°æĿIJæĸĻ
    0.26
    cts
    0.26
    丢
    0.26
    ивание
    0.25
    Activations Density 0.413%

    No Known Activations

    This feature has no known activations.