© 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. 142486
    Prev
    Next
    INDEX
    Explanations

    Islam

    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
    Not in Any Lists

    No Comments

    Negative Logits
     medical
    -0.32
     medically
    -0.32
    åĮ»åѦ
    -0.31
    åĮ»
    -0.29
     Medical
    -0.27
    åĦ¿
    -0.27
    insky
    -0.25
    itre
    -0.24
     dealloc
    -0.24
    åĮ»çĸĹ
    -0.24
    POSITIVE LOGITS
     Independent
    0.28
    çį¨ç«ĭ
    0.26
     independent
    0.26
    Independent
    0.26
     independence
    0.26
     baÅŁÄ±na
    0.24
    -independent
    0.24
     socks
    0.24
    ignment
    0.23
    IZATION
    0.23
    Activations Density 7.034%

    No Known Activations