© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89742
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tình
    -0.26
    minster
    -0.25
     chuyá»ĩn
    -0.24
     <![
    -0.24
    recogn
    -0.24
    prof
    -0.23
    .Arg
    -0.23
    好åIJĥ
    -0.23
     Endpoint
    -0.22
    rate
    -0.22
    POSITIVE LOGITS
    actus
    0.31
    pes
    0.28
    ÐŀС
    0.28
    äºĮæīĭ
    0.28
    elist
    0.28
    arti
    0.28
    确认
    0.26
     ty
    0.26
    麻
    0.26
    asher
    0.26
    Activations Density 2.096%

    No Known Activations

    This feature has no known activations.