© 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. 20-TRANSCODER-HP
    7. 62618
    Prev
    Next
    INDEX
    Explanations

    medical research articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     clinical
    -0.37
     pediatric
    -0.35
     patient
    -0.35
    æĤ£èĢħ
    -0.35
    patient
    -0.33
    临åºĬ
    -0.33
    å©¿
    -0.33
    æĤ£èĢħçļĦ
    -0.33
     medication
    -0.32
     clinically
    -0.32
    POSITIVE LOGITS
    inode
    0.31
     Republic
    0.29
    è¤Ĵ
    0.26
    åħ±åIJĮä½ĵ
    0.26
     Geometry
    0.26
    ammer
    0.25
     Analytics
    0.25
    è®®ä¼ļ
    0.24
    rts
    0.24
     Democr
    0.24
    Activations Density 56.411%

    No Known Activations