© 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. 39452
    Prev
    Next
    INDEX
    Explanations

    Articles and research snippets

    np_max-act · gemini-2.0-flash
    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
    fone
    -0.28
    tru
    -0.27
    ometry
    -0.27
    ikt
    -0.27
    omet
    -0.27
    å¦ĩ
    -0.27
    ilters
    -0.24
    reds
    -0.24
    æĭĦ
    -0.24
     Laundry
    -0.24
    POSITIVE LOGITS
    æĦı大
    0.27
    kke
    0.27
     pil
    0.27
    åĽłèĢĮ
    0.24
    ê²½
    0.24
    uger
    0.24
     Pieces
    0.23
    multip
    0.23
    bery
    0.23
    ddit
    0.23
    Activations Density 0.112%

    No Known Activations