© 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. 12-TRANSCODER-HP
    7. 24034
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    authorize
    -0.27
     Financing
    -0.27
    ä»ĸ们çļĦ
    -0.26
     finance
    -0.26
    uddle
    -0.26
    ëĭĽ
    -0.26
    FIN
    -0.25
    æºIJæºIJä¸įæĸŃ
    -0.25
    Unauthorized
    -0.25
    _FIN
    -0.24
    POSITIVE LOGITS
     shakes
    0.30
    修建
    0.27
    åŀ¢
    0.27
    èħ¥
    0.27
    çĥ½
    0.26
    ben
    0.26
    coni
    0.25
     metro
    0.24
     pneum
    0.24
    AdminController
    0.24
    Activations Density 0.000%

    No Known Activations