© 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. 64883
    Prev
    Next
    INDEX
    Explanations

    Computer-related text

    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
    æĦı大
    -0.27
    util
    -0.26
     personal
    -0.25
     Pos
    -0.25
    -shot
    -0.25
    åĪº
    -0.25
     pace
    -0.24
    agog
    -0.24
    æŃ£æĺ¯åĽłä¸º
    -0.24
    personal
    -0.24
    POSITIVE LOGITS
    ovsky
    0.26
     Boone
    0.25
     promot
    0.25
    éļ¾å¾Ĺ
    0.25
     <![
    0.25
    iness
    0.24
    æĦ§
    0.24
    <![
    0.24
    @Module
    0.24
    ä¸ĵçıŃ
    0.24
    Activations Density 10.475%

    No Known Activations