© 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. 6019
    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
    çŃĸ
    -0.28
    ünst
    -0.26
     Wars
    -0.24
    áŀ¶
    -0.24
    urgent
    -0.24
    .Rad
    -0.24
     vÃŃdeo
    -0.23
    éķ¿æľŁ
    -0.23
    ussen
    -0.23
    çŀ¿
    -0.23
    POSITIVE LOGITS
    ncoder
    0.28
    ä¸Ĭå¹´åIJĮæľŁ
    0.28
    FAULT
    0.27
    æĹłç¼ĺ
    0.27
    å¹´ä¹ĭ
    0.25
    oders
    0.24
    称ä¹ĭ
    0.24
    ä¸Ģè¶Ł
    0.24
    ausal
    0.24
    海绵
    0.24
    Activations Density 1.323%

    No Known Activations

    This feature has no known activations.