© 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. 41511
    Prev
    Next
    INDEX
    Explanations

    government and nobility

    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
    rott
    -0.28
    lexical
    -0.27
    è½®
    -0.27
    åŁĭ
    -0.26
    'l
    -0.25
    indr
    -0.24
     empire
    -0.24
    .Export
    -0.24
    lius
    -0.24
    ç³»ç»ŁçļĦ
    -0.24
    POSITIVE LOGITS
    æĢ»è£ģ
    0.28
    书记
    0.26
    aho
    0.26
    ades
    0.25
    abble
    0.25
    ims
    0.25
    æı´
    0.25
    pack
    0.25
    ivre
    0.24
     Lie
    0.24
    Activations Density 0.111%

    No Known Activations