© 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. 6373
    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
    æĿĤ
    -0.28
    pling
    -0.27
     driv
    -0.27
    ing
    -0.26
    ming
    -0.26
    ä¸ĵå±ŀ
    -0.26
    drive
    -0.25
     drive
    -0.25
    çĻ¾å®¶
    -0.25
    boxes
    -0.24
    POSITIVE LOGITS
    struments
    0.26
    æĸĩåĮĸçļĦ
    0.26
    è¿¢
    0.25
    æĬķåħ¥åĪ°
    0.24
    roys
    0.24
    ENDED
    0.24
    auses
    0.24
     вÑħод
    0.24
    ä¹ŁæĪIJ为
    0.23
     instruments
    0.23
    Activations Density 0.624%

    No Known Activations

    This feature has no known activations.