© 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. 90319
    Prev
    Next
    INDEX
    Explanations

    Code/mathematical expressions

    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
     Shuttle
    -0.27
    Printer
    -0.26
     shuttle
    -0.25
     č↵ č↵
    -0.25
    Picker
    -0.25
     {{$
    -0.24
    çĥ§
    -0.24
    lime
    -0.24
     Bom
    -0.23
      ↵  ↵
    -0.23
    POSITIVE LOGITS
    ä¸Ģèĩ´
    0.28
    hlen
    0.28
    odynam
    0.27
    亡
    0.27
    inct
    0.25
    urent
    0.25
    icina
    0.24
    è£ħ
    0.24
    abol
    0.24
    eração
    0.24
    Activations Density 78.638%

    No Known Activations