© 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. 62633
    Prev
    Next
    INDEX
    Explanations

    code

    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
    isable
    -0.28
     following
    -0.28
    .addWidget
    -0.26
    edException
    -0.25
     latest
    -0.25
    ä¹ĭ乡
    -0.25
     experiment
    -0.24
    ying
    -0.24
     admit
    -0.24
    stad
    -0.24
    POSITIVE LOGITS
    åħĥç´ł
    0.29
    æ¦ķ
    0.27
    -about
    0.25
    .Elements
    0.25
    -aff
    0.25
    ä¸Ģèĩ´
    0.24
    æĹłæīĢ
    0.24
    oras
    0.23
    ä¸įåĩº
    0.23
    ä¼ģä¸ļ
    0.23
    Activations Density 15.173%

    No Known Activations