© 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. 6601
    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
    nces
    -0.28
    .addProperty
    -0.28
    饲
    -0.26
    æĪIJ份
    -0.26
     fibr
    -0.25
    âĢ¦”
    -0.25
    ç¼Ľ
    -0.25
    /column
    -0.25
    column
    -0.25
    å°ĨæĮģç»Ń
    -0.24
    POSITIVE LOGITS
    溢
    0.27
    wal
    0.27
     Walter
    0.26
    ä¸ĢåıĮ
    0.26
    oran
    0.25
    ÑĢÑı
    0.25
    ños
    0.24
     [|
    0.24
    	yy
    0.24
     mot
    0.24
    Activations Density 0.004%

    No Known Activations