© 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. 62620
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
    emann
    -0.29
    aroo
    -0.27
    ERICA
    -0.26
    ï¬ģ
    -0.26
    AZY
    -0.26
    à¹Ģย
    -0.25
    �t
    -0.25
    å¿ĹæĦ¿
    -0.25
    ACHI
    -0.25
    hack
    -0.25
    POSITIVE LOGITS
     bac
    0.28
    æĭ
    0.28
    ç½¹
    0.27
    建设åĴĮ
    0.27
    管çIJĨåĴĮ
    0.26
    è´¨éĩıåĴĮ
    0.26
    æĢ»éĥ¨
    0.26
     Chairman
    0.24
    emm
    0.24
    iddles
    0.24
    Activations Density 7.124%

    No Known Activations