© 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. 22-TRANSCODER-HP
    7. 99190
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pr
    -0.31
     flat
    -0.31
    Ùģات
    -0.28
    flat
    -0.28
    HEMA
    -0.27
     table
    -0.27
    abs
    -0.27
     car
    -0.26
     fact
    -0.26
    FAQ
    -0.26
    POSITIVE LOGITS
    å¿«æį·
    0.27
     ""},↵
    0.26
     lesb
    0.26
    ä»ĸä¼ļ
    0.25
    åįģåĽĽäºĶ
    0.25
    lessly
    0.25
    æŁ¥çľĭæĽ´å¤ļ
    0.24
     PropertyChanged
    0.24
    ç«ŀäºīåĬĽ
    0.24
     Fountain
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.