© 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. 107808
    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
    ...
    -0.34
    ....
    -0.29
     priority
    -0.28
     обÑĭ
    -0.28
     next
    -0.28
    encv
    -0.27
    åµĮ
    -0.27
    ä¸ĭä¸Ģ
    -0.27
    e
    -0.27
    -0.27
    POSITIVE LOGITS
    -Up
    0.27
     ADDR
    0.26
    &B
    0.26
    otime
    0.26
    ÑĢин
    0.25
    Õļ
    0.25
     [&](
    0.25
    .NewRequest
    0.25
    &S
    0.24
    leigh
    0.24
    Activations Density 60.318%

    No Known Activations

    This feature has no known activations.