© 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. 130823
    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
     BN
    -0.25
    URN
    -0.25
     getObject
    -0.25
    ano
    -0.25
     ano
    -0.24
    icker
    -0.24
     citizenship
    -0.23
     ind
    -0.23
     LSU
    -0.23
    æŁľåı°
    -0.23
    POSITIVE LOGITS
    éĢ¶
    0.28
    æĬ¼
    0.25
    [](
    0.25
    æĿ¥è¯´
    0.24
     MC
    0.24
    NC
    0.24
    çļĦ人æĿ¥è¯´
    0.24
    mailto
    0.23
    [W
    0.23
    nost
    0.23
    Activations Density 0.302%

    No Known Activations

    This feature has no known activations.