© 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. 31-TRANSCODER-HP
    7. 17865
    Prev
    Next
    INDEX
    Explanations

    code and computer problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ivet
    -0.30
    immune
    -0.27
    ĮĢ
    -0.26
     Sevilla
    -0.26
    æ´Ĺå¹²åĩĢ
    -0.26
    вен
    -0.25
    çļĦä¸ĢåĪĩ
    -0.25
    issen
    -0.25
    imore
    -0.25
    erland
    -0.25
    POSITIVE LOGITS
    æĥľ
    0.27
     depended
    0.27
    ä¸įåĩĨ
    0.26
     efficiently
    0.26
     optim
    0.26
    æĮ¤
    0.25
    èµĸ
    0.25
    .cent
    0.25
    /linux
    0.24
     smoothly
    0.24
    Activations Density 0.029%

    No Known Activations