© 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. 130921
    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
    æĺł
    -0.28
    å¥Ĺ
    -0.27
    PPER
    -0.26
    çĵ·åĻ¨
    -0.26
    .setContent
    -0.25
    elmet
    -0.25
     getContent
    -0.25
    ATO
    -0.25
    enia
    -0.24
    emen
    -0.24
    POSITIVE LOGITS
    ymous
    0.28
     bre
    0.26
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.26
     pang
    0.24
    osed
    0.24
     further
    0.24
     opposing
    0.23
     Terr
    0.23
     mong
    0.23
     tac
    0.23
    Activations Density 26.107%

    No Known Activations

    This feature has no known activations.