© 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. 108643
    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
     reflective
    -0.28
    иÑĢÑĥем
    -0.25
    makt
    -0.25
    =headers
    -0.25
    eting
    -0.25
     refl
    -0.25
    LOTS
    -0.24
     "%.
    -0.24
    ÑĦизиÑĩеÑģк
    -0.24
     reflections
    -0.24
    POSITIVE LOGITS
    lé
    0.28
    lc
    0.28
    èµĸ
    0.27
    agers
    0.26
    ran
    0.25
     Restoration
    0.24
    agger
    0.24
    å¢Ļ
    0.24
    åĬŀ
    0.24
    çļĦçłĶ究
    0.24
    Activations Density 2.911%

    No Known Activations

    This feature has no known activations.