© 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. 128993
    Prev
    Next
    INDEX
    Explanations

    mathematical simplification

    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
    æİ©
    -0.33
    unks
    -0.30
     appeal
    -0.28
    æĭ¬
    -0.28
     flashes
    -0.27
    flix
    -0.26
    åIJŀ
    -0.26
    ssa
    -0.25
     Earlier
    -0.25
     appeals
    -0.25
    POSITIVE LOGITS
    umeric
    0.34
    /Index
    0.30
     ↵            ↵
    0.26
    èIJ¸
    0.25
    elif
    0.25
    edelta
    0.25
    stry
    0.25
    .Meta
    0.24
    (HttpContext
    0.24
     Palestin
    0.24
    Activations Density 21.003%

    No Known Activations