© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6631
    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
    æŀķ
    -0.27
     adipisicing
    -0.25
    åĪĩå°Ķ
    -0.24
    aspers
    -0.24
     amen
    -0.24
    æĦĨ
    -0.24
     Measure
    -0.24
     Apollo
    -0.23
    .Parser
    -0.23
    ENER
    -0.23
    POSITIVE LOGITS
    åĶ®
    0.27
    è·ijéģĵ
    0.26
    jo
    0.26
    appro
    0.26
    "),
    0.26
    ajo
    0.25
     compound
    0.25
      ↵
    0.25
    满
    0.25
     recogn
    0.25
    Activations Density 0.166%

    No Known Activations

    This feature has no known activations.