© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40026
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ieves
    -0.29
     mask
    -0.26
    itz
    -0.25
    oger
    -0.24
     gener
    -0.24
    ulp
    -0.24
     Pose
    -0.23
    ois
    -0.23
    letic
    -0.23
    .mask
    -0.23
    POSITIVE LOGITS
    ABILITY
    0.31
    hma
    0.27
    羣æĺ¯å¤ª
    0.27
    homme
    0.27
    ä¼Ł
    0.26
     contrasts
    0.26
    è¯Ŀ说
    0.25
     Britann
    0.25
    prus
    0.25
    ascript
    0.24
    Activations Density 5.834%

    No Known Activations

    This feature has no known activations.