© 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. 64765
    Prev
    Next
    INDEX
    Explanations

    a

    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
    硼
    -0.28
    äºĨ解
    -0.26
    çİ°åľº
    -0.26
     funded
    -0.26
    ukt
    -0.25
     financed
    -0.25
    æĹ¢
    -0.25
    çĶ±
    -0.25
    olon
    -0.24
    éĩijåŃĹå¡Ķ
    -0.24
    POSITIVE LOGITS
    就好
    0.27
    gos
    0.27
     obvious
    0.26
    èĢĨ
    0.26
    欢è¿İæĤ¨
    0.26
    æħ¢æħ¢çļĦ
    0.25
    ä¸Ģ个å¤ļ
    0.25
    lers
    0.25
    arian
    0.25
    arians
    0.25
    Activations Density 1.039%

    No Known Activations