© 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. 30-TRANSCODER-HP
    7. 95193
    Prev
    Next
    INDEX
    Explanations

    variations of the word "center"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palmer
    -0.24
    mps
    -0.23
    ugs
    -0.23
    unders
    -0.23
    æħĭ度
    -0.22
    Ñīин
    -0.22
    lington
    -0.22
    checkbox
    -0.22
    ิà¸ĩ
    -0.22
    <byte
    -0.21
    POSITIVE LOGITS
    ä¸Ńå¿ĥ
    1.72
     center
    1.60
    center
    1.41
     centre
    1.37
     Center
    1.31
    Center
    1.29
    -center
    1.25
    _center
    1.23
     central
    1.22
     centers
    1.22
    Activations Density 0.945%

    No Known Activations