© 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. 14-TRANSCODER-HP
    7. 41790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Near
    -0.31
     |-
    -0.28
     CIT
    -0.25
    omen
    -0.25
    âĹ»
    -0.24
     Role
    -0.24
    âĢ¤
    -0.24
    .constructor
    -0.23
    .watch
    -0.23
    Near
    -0.23
    POSITIVE LOGITS
     commissioners
    0.28
     reveals
    0.27
    éĢĭ
    0.27
     reveal
    0.25
    ç½ijé¦ĸ页
    0.25
    æİ¨è¿Ł
    0.25
    Unsafe
    0.24
    æĽ´å¤ļä¿¡æģ¯
    0.24
    å§Ķåijĺä¼ļ
    0.24
    éļIJ约
    0.24
    Activations Density 0.534%

    No Known Activations

    This feature has no known activations.