© 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. 106852
    Prev
    Next
    INDEX
    Explanations

    Excerpts from articles/posts

    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
    hape
    -0.34
    太平
    -0.28
    :numel
    -0.27
    æıIJåīį
    -0.25
    ero
    -0.24
     )}↵↵
    -0.24
    åľ¨è¿ĩ渡
    -0.24
     Bunny
    -0.24
    .ssl
    -0.24
     admins
    -0.24
    POSITIVE LOGITS
     im
    0.29
    cut
    0.27
     sur
    0.26
     chapters
    0.26
     cut
    0.26
     ext
    0.26
    ises
    0.25
     isot
    0.25
     fault
    0.25
     composition
    0.25
    Activations Density 19.919%

    No Known Activations