© 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. 56470
    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
    鬼
    -0.25
     conveying
    -0.25
     electronic
    -0.24
    -kind
    -0.24
    èķĥ
    -0.23
     Pel
    -0.23
    ugs
    -0.22
    ellig
    -0.22
     Sem
    -0.22
    }\\
    -0.22
    POSITIVE LOGITS
    {{{
    0.29
    å®ķ
    0.29
     didn
    0.27
    çĻ»åħ¥
    0.27
    arness
    0.26
    asurer
    0.25
    Editors
    0.25
    üc
    0.25
    etcode
    0.25
     hastily
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.