© 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. 9615
    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
    ailer
    -0.27
    azy
    -0.27
    ',{'
    -0.26
     mobs
    -0.26
    ocks
    -0.25
    atures
    -0.25
    odu
    -0.24
    енÑĮ
    -0.24
     dys
    -0.24
    ç¼Ĩ
    -0.24
    POSITIVE LOGITS
    DataStream
    0.26
    Brains
    0.26
     Livingston
    0.25
    bris
    0.25
    -leading
    0.25
     improv
    0.24
    ighest
    0.24
    !*
    0.24
    ipp
    0.24
    rade
    0.24
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.