© 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. 140774
    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
    NSE
    -0.29
    .$.
    -0.28
    olon
    -0.28
    ismet
    -0.28
    å¸Ń
    -0.26
    ntag
    -0.26
    á»ijt
    -0.26
    ç°§
    -0.25
    enschaft
    -0.24
     kö
    -0.24
    POSITIVE LOGITS
    -reviewed
    0.30
    è¿ĻåĿĹ
    0.26
     rall
    0.25
    emens
    0.25
    CRET
    0.25
     Zuk
    0.25
    cbd
    0.25
    -face
    0.25
    èªĬ
    0.24
     presume
    0.24
    Activations Density 0.706%

    No Known Activations

    This feature has no known activations.