© 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. 142512
    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
    æł¼å±Ģ
    -0.26
     collagen
    -0.26
     columnist
    -0.24
    æ¼¾
    -0.24
    ContentView
    -0.24
    aque
    -0.24
    èĩªåįij
    -0.24
     Sets
    -0.23
    ariate
    -0.23
    马ä¸Ĭå°±
    -0.23
    POSITIVE LOGITS
     enc
    0.28
     surv
    0.26
    unts
    0.26
    spl
    0.26
    TH
    0.26
    ëĭĿ
    0.25
    pered
    0.25
    enc
    0.25
    end
    0.24
    SCP
    0.24
    Activations Density 83.918%

    No Known Activations

    This feature has no known activations.