© 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. 131140
    Prev
    Next
    INDEX
    Explanations

    programming questions

    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
    æīĢæıIJä¾Ľ
    -0.31
    ITU
    -0.26
    çªģ
    -0.26
    ä¾ĽåĽ¾
    -0.25
    æĺĨæĺİ
    -0.25
     protect
    -0.24
    weed
    -0.24
    ensa
    -0.23
    kea
    -0.23
    æķijåij½
    -0.23
    POSITIVE LOGITS
    -Cs
    0.26
    æħ¢æħ¢
    0.26
     catch
    0.25
    æĿł
    0.25
    lbrace
    0.24
    inho
    0.24
    äche
    0.24
    rip
    0.24
    jh
    0.24
    .fi
    0.23
    Activations Density 2.452%

    No Known Activations