© 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. 131220
    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
    æĢĿæĥ³
    -0.27
    çīĮ
    -0.26
    è¯ij
    -0.26
     Rand
    -0.25
    责任ç¼ĸè¾ij
    -0.25
    对è¯Ŀ
    -0.25
     defy
    -0.25
    çīĪæľ¬
    -0.24
    æķ¬ä¸ļ
    -0.24
    !).↵↵
    -0.24
    POSITIVE LOGITS
    orno
    0.28
    _Pin
    0.25
    igr
    0.25
    飲ãģ¿
    0.24
    adan
    0.24
     gou
    0.23
    atum
    0.23
    tright
    0.23
     detect
    0.23
     Gründe
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.