© 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. 142598
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
    uzu
    -0.28
    æ®ĩ
    -0.27
     defer
    -0.26
    奢
    -0.26
     knex
    -0.25
    ataire
    -0.25
    uxt
    -0.25
    vrier
    -0.24
    æĽ¿ãģĪ
    -0.24
     Shelter
    -0.24
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.26
    _MEM
    0.25
    rio
    0.24
     Hyper
    0.24
     ul
    0.24
     und
    0.24
    slots
    0.24
    غÙĬر
    0.23
     Mechanical
    0.23
    .parsers
    0.23
    Activations Density 9.390%

    No Known Activations