© 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. 62720
    Prev
    Next
    INDEX
    Explanations

    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
     cris
    -0.28
    éĢļ讯
    -0.27
     thereafter
    -0.24
     other
    -0.24
     manually
    -0.24
     desperately
    -0.23
     himself
    -0.23
     itself
    -0.23
    ìļĶ
    -0.23
     sacrifices
    -0.23
    POSITIVE LOGITS
    uja
    0.25
    reuse
    0.25
    aptor
    0.25
    æĺ¨æĹ¥
    0.25
    osta
    0.25
    æµ·ä¸Ĭ
    0.25
    ADB
    0.25
    oS
    0.25
    ATAB
    0.25
    oreach
    0.25
    Activations Density 4.993%

    No Known Activations