© 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. 6329
    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
    éķĸ
    -0.28
    çıŃ
    -0.27
    itti
    -0.25
    èĨĺ
    -0.25
    enge
    -0.25
    _DIAG
    -0.25
    鸣
    -0.24
     bigger
    -0.24
    åľŁè±ª
    -0.24
    éĶı
    -0.24
    POSITIVE LOGITS
    ìĤ¼
    0.27
    rex
    0.27
    verified
    0.25
    uite
    0.25
    थ
    0.24
    еÑĢи
    0.24
    True
    0.24
    uments
    0.23
     Manson
    0.23
    å¤ļç§įå½¢å¼ı
    0.23
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.