© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9581
    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
    Negative Logits
    è¡Įä¸ļ
    -0.27
     Watch
    -0.26
    èģĮæĿĥ
    -0.26
    ÄĻd
    -0.24
    .timeout
    -0.24
    åĵ©
    -0.24
     reach
    -0.24
    urope
    -0.24
     Watches
    -0.23
     nett
    -0.23
    POSITIVE LOGITS
    è¿ĩ大
    0.32
    lexport
    0.26
     /************************************************************************
    0.26
    çļĦéģĵçIJĨ
    0.26
    ös
    0.26
    åĻª
    0.26
    è¿Ļä¹Ī大
    0.24
    immers
    0.24
    ined
    0.24
    uges
    0.24
    Activations Density 0.423%

    No Known Activations

    This feature has no known activations.