© 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. 108597
    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
    yro
    -0.26
    åģļåĩºäºĨ
    -0.26
    åģļåĩº
    -0.26
    åķĨæĪ·
    -0.25
    duct
    -0.25
    èĭ¥æĤ¨
    -0.25
    çļĦ好
    -0.24
     '",
    -0.23
    å§Ķæīĺ
    -0.23
    eneg
    -0.23
    POSITIVE LOGITS
    æĿŀ
    0.28
    WithTag
    0.28
     thá»±
    0.26
    adow
    0.25
     Smash
    0.24
    家éŨåı£
    0.24
    åĽĽä¸ªæĸ¹éĿ¢
    0.24
    èĻij
    0.23
    _memcpy
    0.23
    AÃĩÃĥO
    0.23
    Activations Density 2.242%

    No Known Activations

    This feature has no known activations.