© 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. 22-TRANSCODER-HP
    7. 97065
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     tác
    -0.25
    缺ä¹ı
    -0.25
    çļĦä¸Ģç§į
    -0.24
    åĮ®ä¹ı
    -0.24
     lacks
    -0.24
    ç´¢åıĸ
    -0.24
    alia
    -0.23
    人们对
    -0.23
    äºĨä¸Ģä¸ĭ
    -0.23
    åºŀ
    -0.23
    POSITIVE LOGITS
    usz
    0.24
    Industry
    0.24
     Rule
    0.24
     cud
    0.24
    ustrial
    0.24
     PROCUREMENT
    0.23
    -eff
    0.23
    ppers
    0.23
    strument
    0.23
    èIJ¥ä¸ļæī§çħ§
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.