© 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. 6825
    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
    issan
    -0.29
    едÑĮ
    -0.28
     grop
    -0.28
    åIJĥäºı
    -0.27
    edom
    -0.27
    ä½ıäºĨ
    -0.27
    ellas
    -0.26
     traced
    -0.25
    isos
    -0.25
    ackbar
    -0.25
    POSITIVE LOGITS
    éĺľ
    0.27
    åħijçİ°
    0.26
     MCP
    0.26
     rubber
    0.25
    èŀŁ
    0.25
    ä¹³
    0.24
    <Float
    0.24
    itizer
    0.24
    èĿĩ
    0.24
     hardwood
    0.24
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.