© 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. 99063
    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
    å·¡
    -0.27
    ç©¿
    -0.26
    ä¼ļåIJĮ
    -0.25
    sylvania
    -0.25
    è¡ĵ
    -0.24
    eba
    -0.24
     recalling
    -0.24
    çĮİ
    -0.24
    åħ¨
    -0.23
    éĽ³
    -0.23
    POSITIVE LOGITS
     æĽ´æĸ°
    0.26
    次
    0.26
     clearTimeout
    0.26
     ***↵
    0.24
    缸åħ³çļĦ
    0.24
    çݰ代社ä¼ļ
    0.24
    _printf
    0.24
    lon
    0.23
     cog
    0.23
    né
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.