© 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. 6540
    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
    cor
    -0.29
     cor
    -0.28
     correlation
    -0.28
    _cor
    -0.28
    åĨł
    -0.28
    inet
    -0.27
     optim
    -0.26
     correlations
    -0.25
    æĪ¿
    -0.25
    ablo
    -0.25
    POSITIVE LOGITS
    blocking
    0.25
     Protector
    0.24
     Skywalker
    0.23
     productName
    0.23
    isque
    0.23
     עצ
    0.23
     Tantra
    0.23
     Says
    0.23
    Ctrls
    0.23
    æijĩ头
    0.23
    Activations Density 0.225%

    No Known Activations

    This feature has no known activations.