© 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. 14-TRANSCODER-HP
    7. 41699
    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
    Negative Logits
     neutrality
    -0.29
    wort
    -0.26
    ä¸Ģåı¥è¯Ŀ
    -0.26
    Mount
    -0.26
     Heard
    -0.25
    ublic
    -0.25
    CORD
    -0.25
    ugg
    -0.24
     Ownership
    -0.24
    éĻ¡
    -0.24
    POSITIVE LOGITS
    ÑģÑĤва
    0.26
    .management
    0.26
     Mavericks
    0.26
     "{"
    0.25
    èĻŁ
    0.25
    åIJĪ
    0.25
     Lion
    0.25
     lif
    0.24
     getSystemService
    0.24
     Sext
    0.24
    Activations Density 0.119%

    No Known Activations

    This feature has no known activations.