© 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. 31-TRANSCODER-HP
    7. 19778
    Prev
    Next
    INDEX
    Explanations

    pilots and drivers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĽĺ
    -0.28
    èĪ¹åıª
    -0.28
    mare
    -0.27
     Hoover
    -0.26
     buses
    -0.26
     tren
    -0.26
     rect
    -0.25
    é£ŀæľº
    -0.25
    berman
    -0.25
     Mueller
    -0.24
    POSITIVE LOGITS
     pilot
    0.81
     Pilot
    0.66
     pil
    0.66
    å¼ķæĵİ
    0.63
     pilots
    0.63
     engine
    0.60
     Pil
    0.59
     driver
    0.58
     mechanic
    0.54
    驾驶åijĺ
    0.54
    Activations Density 5.987%

    No Known Activations