© 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. 20-TRANSCODER-HP
    7. 140589
    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
    Negative Logits
    clipse
    -0.27
     reversible
    -0.26
    _OVERFLOW
    -0.24
    leta
    -0.24
    arResult
    -0.24
     (~(
    -0.23
    _none
    -0.23
    å¸ĪåħĦ
    -0.23
    åľĬ
    -0.23
     none
    -0.23
    POSITIVE LOGITS
    ugas
    0.27
    ẫu
    0.27
    å·¡
    0.27
    éĺ²æ²»
    0.26
     -,
    0.26
    èĬĿ
    0.25
    à¹Ĥà¸Ļ
    0.25
    继
    0.25
    éĵĤ
    0.25
    èµĦ讯
    0.24
    Activations Density 25.691%

    No Known Activations

    This feature has no known activations.