© 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. 62751
    Prev
    Next
    INDEX
    Explanations

    for

    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
    abay
    -0.27
    èİŀ
    -0.27
    ramework
    -0.26
    ç«ĭ
    -0.26
    ullah
    -0.25
     anytime
    -0.25
    躲éģ¿
    -0.23
    丰
    -0.23
    umann
    -0.23
    lez
    -0.22
    POSITIVE LOGITS
    俱
    0.29
     ones
    0.28
     whose
    0.27
    ä¸įéĢļ
    0.27
    æ°ª
    0.26
    çĶ¨æĪ·çļĦ
    0.25
    \Builder
    0.25
    faker
    0.25
    è´¿
    0.24
    ãģªãĤĤãģ®
    0.24
    Activations Density 67.808%

    No Known Activations