© 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. 129814
    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
    åĪĩãĤĮ
    -0.24
    ière
    -0.24
    Kit
    -0.24
    SharedPtr
    -0.24
    orry
    -0.24
    VERS
    -0.23
    lineno
    -0.23
    鸰
    -0.23
    för
    -0.23
     interests
    -0.23
    POSITIVE LOGITS
    çªģ
    0.26
    Spo
    0.26
    tps
    0.25
    odem
    0.24
    ’.↵↵
    0.24
    /xhtml
    0.24
    尽头
    0.24
    xmm
    0.24
    溶
    0.24
     Ost
    0.23
    Activations Density 18.124%

    No Known Activations

    This feature has no known activations.