© 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. 142509
    Prev
    Next
    INDEX
    Explanations

    general text

    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
    åĮħ
    -0.31
    criptor
    -0.28
     entry
    -0.27
    贯彻
    -0.26
    å°ıç¼ĸ
    -0.26
    èĩ¾
    -0.25
    Bundle
    -0.25
     bag
    -0.25
    itet
    -0.25
    uit
    -0.25
    POSITIVE LOGITS
    ETH
    0.27
     afar
    0.26
    è¸ı
    0.25
    ä¸į平衡
    0.25
    'em
    0.25
    身
    0.24
     bal
    0.24
    acies
    0.24
     pH
    0.24
     dá
    0.24
    Activations Density 1.114%

    No Known Activations