© 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. 6529
    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
    åħ³äºİæĪij们
    -0.30
     sund
    -0.29
    rov
    -0.28
    èĤĸ
    -0.27
    ä¸įå®Į
    -0.26
     traded
    -0.26
    acen
    -0.26
    ês
    -0.25
    èle
    -0.24
     compiler
    -0.24
    POSITIVE LOGITS
    çŃı
    0.27
    .Must
    0.25
     forcefully
    0.25
    -heart
    0.24
    Visibility
    0.24
    æĬ½çĥŁ
    0.23
     pea
    0.23
    uggestions
    0.23
    hints
    0.23
    ibern
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.