© 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. 90263
    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
    çļĦå°±æĺ¯
    -0.28
    å¤¸å¼ł
    -0.26
    çļĦåŁİå¸Ĥ
    -0.26
    æĬĬæīĭ
    -0.25
    YW
    -0.24
     rew
    -0.24
    ç»Ļä½ł
    -0.24
     ench
    -0.24
    ç¢Ł
    -0.24
    ylv
    -0.24
    POSITIVE LOGITS
    edes
    0.29
    è´Ńç½®
    0.26
    ENTA
    0.26
    ä¹īåĬ¡
    0.23
    eda
    0.23
    вл
    0.23
    è¡Į为
    0.23
    ãĥIJãĤ¤
    0.23
    ä¸ĢåıĮ
    0.23
    vie
    0.23
    Activations Density 3.490%

    No Known Activations

    This feature has no known activations.