© 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. 6199
    Prev
    Next
    INDEX
    Explanations

    plug

    np_max-act · gemini-2.0-flash
    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
    üzü
    -0.24
    alis
    -0.23
    大å±Ģ
    -0.23
     EventType
    -0.23
    pty
    -0.23
    .EventQueue
    -0.22
     ViewData
    -0.21
    acre
    -0.21
    UBY
    -0.21
    ضا
    -0.21
    POSITIVE LOGITS
    <?,
    0.26
     fa
    0.26
    per
    0.25
     ï
    0.25
    GED
    0.25
     stick
    0.25
     hand
    0.24
     presence
    0.24
    ä¸ĭæĿ¥çļĦ
    0.24
     [
    0.24
    Activations Density 2.539%

    No Known Activations