© 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. 39694
    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
    ARNING
    -0.31
    rog
    -0.27
    jax
    -0.26
    ogn
    -0.25
    otope
    -0.25
    樽
    -0.25
    apped
    -0.24
    leur
    -0.24
    lor
    -0.24
    çºł
    -0.24
    POSITIVE LOGITS
    çħ§æł·
    0.26
    thought
    0.26
    æ³ķ令
    0.26
    åĩłä¹İæĺ¯
    0.23
     accompany
    0.23
     Minds
    0.23
     ..↵↵
    0.23
     discontin
    0.23
    _DF
    0.23
    æĹģ
    0.23
    Activations Density 1.028%

    No Known Activations

    This feature has no known activations.