© 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. 140561
    Prev
    Next
    INDEX
    Explanations

    buying, purchasing, acquisition

    np_max-act · gemini-2.0-flash
    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
     Chaos
    -0.27
    为æĤ¨
    -0.26
    intendent
    -0.25
    ILI
    -0.25
    hausen
    -0.23
    åħ¥å¢ĥ
    -0.23
    éĻ©
    -0.23
    éĿ¢åŃĶ
    -0.23
     vacc
    -0.23
    reed
    -0.23
    POSITIVE LOGITS
    éĶĻè¿ĩ
    0.27
     ignoring
    0.27
    -transitional
    0.26
    *dx
    0.25
    æIJŃ建
    0.25
     separately
    0.25
    éķĢéĶĮ
    0.25
    åĹī
    0.25
    SetUp
    0.24
    .Bundle
    0.24
    Activations Density 12.641%

    No Known Activations