© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64250
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    个交æĺĵ
    -0.26
    å°ıé¢Ŀ
    -0.26
    Öģ
    -0.25
     è¾
    -0.25
    dbContext
    -0.25
    elig
    -0.24
    cing
    -0.24
    zell
    -0.24
    ombok
    -0.24
    åIJ¦
    -0.24
    POSITIVE LOGITS
    .Driver
    0.27
     Fill
    0.27
    orable
    0.27
    åı«æĪij
    0.26
     Gather
    0.26
     mus
    0.26
    зав
    0.25
    erman
    0.25
     fillColor
    0.25
     cooperating
    0.25
    Activations Density 0.077%

    No Known Activations

    This feature has no known activations.