© 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. 106782
    Prev
    Next
    INDEX
    Explanations

    formulas and 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
    åŁ¹èĤ²
    -0.26
    eturn
    -0.26
    åѵ
    -0.26
    é¼ĵèĪŀ
    -0.26
    ither
    -0.25
    .java
    -0.25
    åĿŀ
    -0.25
    .onStart
    -0.24
    åħ»æĪIJ
    -0.24
     preload
    -0.24
    POSITIVE LOGITS
    åĽ½åĬ¡
    0.25
    åijĺ
    0.24
    ha
    0.24
    resenter
    0.24
     rhyme
    0.24
    åį¢
    0.24
     mer
    0.23
    å°Ķ
    0.23
     {}.
    0.23
    ire
    0.23
    Activations Density 5.308%

    No Known Activations