© 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. 108595
    Prev
    Next
    INDEX
    Explanations

    constitution

    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
    rift
    -0.29
    StringUtil
    -0.28
    angan
    -0.27
    æĭĽèĤ¡
    -0.26
    æĿ¥ä¸´
    -0.25
    _receipt
    -0.24
    squ
    -0.24
    ç¼¥
    -0.23
     Sanity
    -0.23
     Charl
    -0.23
    POSITIVE LOGITS
    isation
    0.29
    ile
    0.28
    iard
    0.28
    ization
    0.27
     matter
    0.26
    æĬĺ
    0.25
    ↵
    0.25
     E
    0.25
     independent
    0.25
    ãĤıãĤĮ
    0.25
    Activations Density 6.489%

    No Known Activations