© 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. 32-TRANSCODER-HP
    7. 43032
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     order
    -0.84
    order
    -0.69
     Order
    -0.63
    _order
    -0.58
    (order
    -0.57
    .order
    -0.56
    Order
    -0.55
     orders
    -0.54
    'order
    -0.54
    -order
    -0.54
    POSITIVE LOGITS
    tures
    0.27
    herits
    0.26
    ulet
    0.26
    iley
    0.26
    tree
    0.26
    TU
    0.25
    (([
    0.24
    ä¿Ŀä½ı
    0.24
    SE
    0.23
    TREE
    0.23
    Activations Density 0.005%

    No Known Activations