© 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. 39440
    Prev
    Next
    INDEX
    Explanations

    Web data and code 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
     zaj
    -0.27
     frozen
    -0.27
    icios
    -0.27
    izzer
    -0.26
    ificial
    -0.26
    æĸ¯åŁº
    -0.25
    clusive
    -0.25
    åĨ·åĨ»
    -0.25
    -shadow
    -0.25
    åĨ»ç»ĵ
    -0.25
    POSITIVE LOGITS
    ¼
    0.29
    åĨĴçĿĢ
    0.25
    Publisher
    0.25
     airflow
    0.25
    åij¼
    0.24
    ProgressHUD
    0.24
    !';↵
    0.24
    Contains
    0.23
    (kwargs
    0.23
    墩
    0.23
    Activations Density 0.826%

    No Known Activations