© 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. 128923
    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
    shine
    -0.30
    айн
    -0.26
    cratch
    -0.24
    红æĹĹ
    -0.24
     krist
    -0.24
    ayout
    -0.23
    ä¸Ģåı¥è¯Ŀ
    -0.23
    )":
    -0.23
    éļIJå½¢
    -0.23
    ensch
    -0.23
    POSITIVE LOGITS
     rem
    0.27
     Rem
    0.27
    æĦŁ
    0.26
     inf
    0.26
     FD
    0.24
    ?url
    0.24
     Rif
    0.24
    Rem
    0.24
    ///<
    0.24
    éĥ½ä¸į
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.