© 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. 4786
    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
    iled
    -0.26
    uuid
    -0.24
    heed
    -0.24
    ilateral
    -0.24
    itious
    -0.24
    ifdef
    -0.23
    mur
    -0.23
    GtkWidget
    -0.23
    .Reflection
    -0.23
    odia
    -0.23
    POSITIVE LOGITS
     Crossing
    0.29
    edBy
    0.27
     crossings
    0.27
     necesario
    0.26
    ANCEL
    0.25
    udden
    0.25
     crossing
    0.24
    交åıī
    0.24
    å¦Ĥä½ķåİ»
    0.24
    ED
    0.24
    Activations Density 0.203%

    No Known Activations

    This feature has no known activations.