© 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. 18-TRANSCODER-HP
    7. 90249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    jan
    -0.32
    tent
    -0.28
    æķ´ä½ĵ
    -0.28
    VA
    -0.26
     Overall
    -0.26
     chasing
    -0.25
    kad
    -0.25
    éĩij
    -0.25
    efs
    -0.25
    icc
    -0.25
    POSITIVE LOGITS
    ieval
    0.30
    æŀ¥
    0.28
    æĺ¯æľĢ好çļĦ
    0.28
    нÑıÑĤи
    0.25
    EDURE
    0.25
    RunWith
    0.24
    å½ķçĶ¨
    0.24
    alty
    0.24
     retire
    0.24
     solved
    0.24
    Activations Density 9.602%

    No Known Activations

    This feature has no known activations.