© 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. 39576
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs

    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
    opol
    -0.25
    çªĺ
    -0.25
    -con
    -0.24
    mist
    -0.24
    pie
    -0.24
    EqualTo
    -0.23
     scissors
    -0.23
    cron
    -0.23
    setting
    -0.23
    appe
    -0.23
    POSITIVE LOGITS
    imar
    0.27
    para
    0.27
    //↵↵↵
    0.26
    .wrap
    0.26
    ugins
    0.25
    ä¿ŀ
    0.25
    (Unit
    0.24
     interpolate
    0.24
     //~
    0.24
    /unit
    0.24
    Activations Density 1.610%

    No Known Activations