© 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. 27-TRANSCODER-HP
    7. 9769
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    TN
    -0.26
    å¾·æĭī
    -0.25
    .ga
    -0.25
    agate
    -0.24
     intervention
    -0.24
    Prefix
    -0.24
    lickr
    -0.24
     stal
    -0.23
     intervening
    -0.23
    微信åħ¬ä¼Ĺ
    -0.23
    POSITIVE LOGITS
    VERS
    0.29
    vers
    0.29
    verse
    0.27
    åİ¢
    0.25
    ium
    0.25
     ì¡´
    0.24
    vfs
    0.24
    banks
    0.23
    ikit
    0.23
    åĿIJçĿĢ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.