© 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. 6644
    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
    究
    -0.29
    asion
    -0.27
     Independent
    -0.26
     independent
    -0.26
    ä¸ĢåIJij
    -0.25
     Directive
    -0.24
    说è¿ĩ
    -0.24
    ampie
    -0.24
    .directive
    -0.24
    .sc
    -0.24
    POSITIVE LOGITS
     Humb
    0.30
    .calls
    0.28
    æĢ§è´¨
    0.26
     DataContext
    0.26
    NotificationCenter
    0.26
    Paginator
    0.26
    HOST
    0.25
    arl
    0.25
     nostr
    0.25
    localhost
    0.25
    Activations Density 0.150%

    No Known Activations

    This feature has no known activations.