© 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. 129178
    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
     eg
    -0.29
    isée
    -0.27
     regarded
    -0.27
    owitz
    -0.26
    kü
    -0.26
    uide
    -0.25
    ugi
    -0.25
    ÑĤоÑĢ
    -0.25
    çŁ¢
    -0.25
    OfWork
    -0.25
    POSITIVE LOGITS
    åıĪ好
    0.32
    TEM
    0.30
    詹å§Ĩ
    0.28
    ÑĪим
    0.27
    亵
    0.26
    åĪĨåĮĸ
    0.25
     Jame
    0.25
    ạn
    0.24
     AUTHOR
    0.23
    ENTS
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.