© 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. 88999
    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
    æ¯ĶæĪij
    -0.29
    缸åħ³ä¿¡æģ¯
    -0.25
    èĬ¬
    -0.25
     flies
    -0.24
     OrderedDict
    -0.24
     Vend
    -0.24
    [](
    -0.23
    æ¯Ķ
    -0.23
     namedtuple
    -0.23
    é£ŀ
    -0.23
    POSITIVE LOGITS
    æĢł
    0.25
    gly
    0.24
     hous
    0.24
    亥
    0.24
    临
    0.24
     Church
    0.23
    ddd
    0.23
    Church
    0.23
    iva
    0.23
    tips
    0.23
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.