© 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. 99288
    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
     Lansing
    -0.29
    /welcome
    -0.28
    agine
    -0.27
    usher
    -0.27
    hä
    -0.27
    labs
    -0.27
     rooting
    -0.27
    OLVE
    -0.24
    Ļ¨
    -0.24
    BUF
    -0.24
    POSITIVE LOGITS
     Cult
    0.27
    æľĿé²ľ
    0.27
    cult
    0.26
    åĮ¯
    0.26
    å§Ķä¼ļ
    0.25
    社ä¼ļæķĪçĽĬ
    0.25
    è´©åįĸ
    0.25
    ilda
    0.24
    arters
    0.24
    åºķ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.