© 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. 40643
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oner
    -0.27
    为æĬĵ
    -0.26
     category
    -0.26
    Circle
    -0.26
    åħ±èµ¢
    -0.26
     Circle
    -0.26
     circles
    -0.25
     rank
    -0.25
     Rank
    -0.25
    imb
    -0.25
    POSITIVE LOGITS
    YL
    0.30
    è½®
    0.28
    é£İäºij
    0.26
    éŀł
    0.26
    ÙĬÙĦا
    0.26
    arro
    0.25
    çİij
    0.25
    YLE
    0.25
    驹
    0.25
    uum
    0.25
    Activations Density 0.183%

    No Known Activations