© 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. 90128
    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
    okit
    -0.29
    为æŃ¢
    -0.25
    sher
    -0.25
    ppe
    -0.24
    rell
    -0.24
     pari
    -0.24
    elden
    -0.24
     Ner
    -0.24
     chi
    -0.23
     Palestin
    -0.23
    POSITIVE LOGITS
    æ´»
    0.33
     impressed
    0.28
     trÃŃ
    0.26
    顺åºĶ
    0.25
     lowercase
    0.25
    try
    0.25
     cleans
    0.25
     lei
    0.24
    TRY
    0.24
    ä¼ļç»Ļ
    0.24
    Activations Density 0.126%

    No Known Activations

    This feature has no known activations.