© 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. 112899
    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
     heels
    -0.29
    åĩºåĬ¨
    -0.27
    å½¢
    -0.26
    omain
    -0.25
    ÎIJ
    -0.24
    峪
    -0.23
    -caption
    -0.23
    æĺ¾ç¤º
    -0.23
    iad
    -0.23
    undi
    -0.23
    POSITIVE LOGITS
    輩
    0.24
    æľīæľºä¼ļ
    0.24
    éĽį
    0.24
     stub
    0.23
    еннÑĥÑİ
    0.23
     butterknife
    0.23
    VOKE
    0.23
     Serialized
    0.23
    åĥ¹æł¼
    0.23
    alloc
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.