© 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. 18-TRANSCODER-HP
    7. 88235
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĸĵ
    -0.26
    éĥİ
    -0.25
     Setter
    -0.24
    BER
    -0.24
    errer
    -0.24
    ced
    -0.23
    .Names
    -0.23
     aff
    -0.23
    VA
    -0.23
    /release
    -0.23
    POSITIVE LOGITS
    éħ·
    0.31
    ¦Ĥ
    0.29
    stride
    0.26
    请åıĬæŶ
    0.25
    wiki
    0.24
    .pkg
    0.24
    filesize
    0.24
     scouts
    0.24
    é¦ĸåħĪæĺ¯
    0.24
    hipster
    0.24
    Activations Density 3.179%

    No Known Activations