© 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. 108760
    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
     arts
    -0.27
    è¿Ļ段
    -0.27
     art
    -0.27
    èīºæľ¯
    -0.26
    ells
    -0.26
    ä¸ĸçķĮçļĦ
    -0.24
    esch
    -0.24
     mistaken
    -0.24
    GST
    -0.24
    iske
    -0.23
    POSITIVE LOGITS
    apos
    0.28
    çijŀ
    0.27
     Shack
    0.26
    räume
    0.25
    пÑĢоиз
    0.23
    ofire
    0.23
    OfWork
    0.23
     Reaper
    0.23
    newInstance
    0.23
    ropic
    0.23
    Activations Density 41.744%

    No Known Activations

    This feature has no known activations.