© 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. 64617
    Prev
    Next
    INDEX
    Explanations

    ellow

    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
    oupper
    -0.28
    PAD
    -0.26
     treff
    -0.25
    unnable
    -0.25
    .Pages
    -0.23
     <![
    -0.23
    (KP
    -0.23
    .Ac
    -0.23
    XPath
    -0.23
    â¿
    -0.22
    POSITIVE LOGITS
    æ°¸ä¸į
    0.27
    ienza
    0.26
     permanent
    0.25
    URITY
    0.25
    hands
    0.25
    èıĬèĬ±
    0.25
    iless
    0.25
    STA
    0.25
     tác
    0.25
    aus
    0.25
    Activations Density 3.215%

    No Known Activations