© 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. 142766
    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
    .Domain
    -0.25
    主è¦ģçĶ¨äºİ
    -0.25
    street
    -0.25
     enough
    -0.24
    åı¯çĶ¨äºİ
    -0.24
    BJ
    -0.24
     Enough
    -0.24
    Ä©nh
    -0.24
     street
    -0.24
    assel
    -0.24
    POSITIVE LOGITS
    硼
    0.29
    [$_
    0.27
     synergy
    0.26
    寻
    0.26
    entr
    0.25
     bor
    0.25
    ä¸įè§ģ
    0.25
     suggestions
    0.25
    åħ¥åĽ´
    0.24
    çļĦåŃĺåľ¨
    0.24
    Activations Density 57.336%

    No Known Activations

    This feature has no known activations.