© 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. 5037
    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
    olumn
    -0.27
     fairness
    -0.26
    itaire
    -0.26
    ardu
    -0.26
    åĮ¦
    -0.25
    Iron
    -0.25
    nement
    -0.24
    ç»
    -0.24
    两端
    -0.24
    ']}'
    -0.24
    POSITIVE LOGITS
    åľ¨æł¡
    0.29
    æįķæįī
    0.28
     cursed
    0.28
    uce
    0.27
    åľ¨è¿Ļæĸ¹éĿ¢
    0.26
    ç³ķ
    0.26
    ä¸ĭæĿ¥
    0.25
    umed
    0.25
    вл
    0.24
    render
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.