© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40393
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cheon
    -0.26
    æľķ
    -0.26
    edia
    -0.26
    fork
    -0.25
    åĪĨæł¡
    -0.25
    æľīä¸Ģ天
    -0.25
    ZY
    -0.24
    ä¾Ľç»Ļ
    -0.24
    åĽ½åĢº
    -0.24
     gradu
    -0.24
    POSITIVE LOGITS
     pint
    0.30
    æĺİæĺ¾
    0.29
     clearly
    0.27
    DownList
    0.26
    év
    0.25
     pul
    0.25
     Eastern
    0.24
    ini
    0.24
    avi
    0.23
    .plugin
    0.23
    Activations Density 2.293%

    No Known Activations

    This feature has no known activations.