© 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. 39635
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific terminology

    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
    ican
    -0.28
     negativity
    -0.27
    esen
    -0.26
    ẩm
    -0.25
     promoted
    -0.25
    æĶ¾æīĭ
    -0.24
    izacao
    -0.24
    ç±į
    -0.23
    segue
    -0.23
     laid
    -0.23
    POSITIVE LOGITS
    çīĸ
    0.28
    ,test
    0.25
    TRL
    0.25
    (pad
    0.25
    çĽ²
    0.25
    ifax
    0.24
     Appliances
    0.24
    imp
    0.24
    (acc
    0.24
    éĥ
    0.24
    Activations Density 2.917%

    No Known Activations