© 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. 88124
    Prev
    Next
    INDEX
    Explanations

    Website UI elements

    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
    åĽºå®ļçļĦ
    -0.30
    åºıåĪĹ
    -0.27
    [](
    -0.27
    rox
    -0.26
    è¾ĩ
    -0.25
    æľŁåĨħ
    -0.25
    å½¼æѤ
    -0.24
    #ab
    -0.24
    [ch
    -0.24
    datas
    -0.24
    POSITIVE LOGITS
    èĮ«èĮ«
    0.26
     booth
    0.25
    çĥ«
    0.25
    à¸Ļาม
    0.25
    æݾ
    0.25
    uffer
    0.25
    (Path
    0.24
     fare
    0.24
     Herman
    0.24
    漫éķ¿
    0.24
    Activations Density 8.677%

    No Known Activations