© 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. 23-TRANSCODER-HP
    7. 25528
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oley
    -0.27
    inox
    -0.27
     identified
    -0.26
    å¼ķåħ¥
    -0.25
    ilon
    -0.24
    HANDLE
    -0.24
    ingle
    -0.24
    omid
    -0.24
    ä¿¡ä»»
    -0.23
    让åŃ©åŃIJ
    -0.23
    POSITIVE LOGITS
    ĥģ
    0.25
    ç½ijé¦ĸ页
    0.24
    oured
    0.24
     Hearts
    0.24
    SENT
    0.24
    ItemList
    0.24
     Yesterday
    0.23
     Haj
    0.23
     warmly
    0.23
     Trav
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.