© 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. 6719
    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
    åĬĪ
    -0.30
    BI
    -0.29
    ?v
    -0.27
    ä¼ĹçĶŁ
    -0.26
     cols
    -0.25
    intr
    -0.24
    æĢ¨
    -0.24
    æĭĨ
    -0.23
     biz
    -0.23
    cov
    -0.23
    POSITIVE LOGITS
    __[
    0.27
    urma
    0.26
    :Add
    0.25
    elden
    0.24
    ]=[
    0.24
    pson
    0.23
    imony
    0.23
    ponsive
    0.23
     pedals
    0.23
    åŁ¹åħ»åѦçĶŁ
    0.23
    Activations Density 0.081%

    No Known Activations

    This feature has no known activations.