© 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. 5079
    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
    ismic
    -0.30
    ches
    -0.29
    ç¼ĸ
    -0.27
    eltas
    -0.26
    æ²®
    -0.26
     libre
    -0.25
    filer
    -0.25
    lyn
    -0.25
    alen
    -0.25
    usi
    -0.24
    POSITIVE LOGITS
    æ³ķå¾ĭè§Ħå®ļ
    0.28
    ç©¿æ¢Ń
    0.27
    енд
    0.27
     bÄĥng
    0.25
     Wand
    0.25
    èľĤ
    0.25
     Law
    0.24
    è¿ĺæĺ¯è¦ģ
    0.24
    æł¼
    0.24
    æ¯Ľ
    0.24
    Activations Density 0.106%

    No Known Activations

    This feature has no known activations.