© 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. 4979
    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
    do
    -0.27
    peri
    -0.26
    å±¥èģĮ
    -0.26
    ick
    -0.25
     breed
    -0.24
     peri
    -0.24
    è´ŀ
    -0.24
    utar
    -0.23
    arem
    -0.23
    ique
    -0.23
    POSITIVE LOGITS
    paque
    0.28
    ä¸Ģ个å¤ļ
    0.26
    alone
    0.26
    isma
    0.26
     Pace
    0.25
    è¶Ĭè¿ĩ
    0.25
    çļĦæ¯ĶèµĽ
    0.25
    è·ĭ
    0.24
    hv
    0.23
     Pb
    0.23
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.