© 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. 20-TRANSCODER-HP
    7. 129363
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ缮åħī
    -0.26
    åīĮ
    -0.26
     pearls
    -0.26
     inds
    -0.24
    kı
    -0.24
    okus
    -0.24
     Commit
    -0.24
    _COMMIT
    -0.23
    DDS
    -0.23
    ros
    -0.23
    POSITIVE LOGITS
    éĤ£äºº
    0.28
    åħ¸
    0.27
     '+
    0.27
    Ã¤ÃŁ
    0.27
    ä¸ĭéĿ¢æĺ¯
    0.26
    åıĮéĩį
    0.25
    obi
    0.25
    å½ĵäºĭ
    0.25
    ä¸Ģå®ļæĺ¯
    0.24
    å¹½é»ĺ
    0.24
    Activations Density 0.102%

    No Known Activations

    This feature has no known activations.