© 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. 39413
    Prev
    Next
    INDEX
    Explanations

    Science and medicine

    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
    ipt
    -0.31
    ippers
    -0.28
    ģ
    -0.27
    ãĥ¼ãĥ³
    -0.26
     gener
    -0.25
     served
    -0.25
    shot
    -0.24
     Drinks
    -0.24
    Tickets
    -0.24
    âĦ°
    -0.24
    POSITIVE LOGITS
    纲
    0.29
    untas
    0.29
    leness
    0.29
    èĥ½åĬĽåĴĮ
    0.27
    ility
    0.26
     Federation
    0.25
     Division
    0.25
     insensitive
    0.25
     wholes
    0.24
    pus
    0.24
    Activations Density 1.599%

    No Known Activations