© 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. 88834
    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
    ilig
    -0.25
    patch
    -0.25
    athi
    -0.24
     patches
    -0.24
     efficacy
    -0.23
     geliÅŁ
    -0.23
    ä¸ĢåĪĨ
    -0.23
    ãģ§ãģįãģŁ
    -0.23
    ates
    -0.22
     intact
    -0.22
    POSITIVE LOGITS
    ä¹°çļĦ
    0.26
    riere
    0.26
     getClass
    0.24
     uncert
    0.24
    è¿ĻäºĽäºº
    0.23
    ë§Ŀ
    0.23
    <D
    0.23
    ç½ijé¦ĸ页
    0.22
    Fish
    0.22
    rü
    0.22
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.