© 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. 39609
    Prev
    Next
    INDEX
    Explanations

    Code and addresses

    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
     seo
    -0.25
    _hr
    -0.24
     Colt
    -0.24
    HAV
    -0.24
    éĻį
    -0.23
    fahren
    -0.23
    æ³¢çī¹
    -0.23
     themes
    -0.23
    -lived
    -0.23
    еÑĩа
    -0.23
    POSITIVE LOGITS
     Epic
    0.27
    oidal
    0.26
    еле
    0.25
    arily
    0.24
    ilater
    0.24
    ardon
    0.24
    åħ®
    0.24
    бил
    0.24
    "#
    0.23
    ippi
    0.23
    Activations Density 0.156%

    No Known Activations