© 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. 142407
    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
    æ¹ĸåĮº
    -0.27
     lòng
    -0.26
    å¤įæĿĤ
    -0.24
    ä¸į容
    -0.24
    转æĬĺ
    -0.23
    åıªä¸º
    -0.23
    åĺĮ
    -0.23
     Miller
    -0.22
    çŃ¾
    -0.22
    转åIJij
    -0.22
    POSITIVE LOGITS
     ula
    0.26
    subtype
    0.26
    artment
    0.25
    (UI
    0.24
    å¦ŀ
    0.24
    -Pack
    0.24
    ulia
    0.24
    æľīçĶ¨çļĦ
    0.24
     fragment
    0.23
    ulent
    0.23
    Activations Density 10.310%

    No Known Activations

    This feature has no known activations.