© 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. 108590
    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
     Wonderland
    -0.27
    uale
    -0.24
    æŁĵ
    -0.23
     Boh
    -0.23
    .percent
    -0.23
    ollipop
    -0.23
    [dim
    -0.23
    uggest
    -0.23
    uchs
    -0.23
     underestimate
    -0.23
    POSITIVE LOGITS
    xit
    0.29
    顾éĹ®
    0.26
    zone
    0.26
    ä¸Ģ个éĹ®é¢ĺ
    0.26
     rust
    0.26
     aug
    0.26
    pects
    0.25
    ucker
    0.25
    ÑĢаж
    0.25
    ÙĤات
    0.24
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.