© 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. 90304
    Prev
    Next
    INDEX
    Explanations

    to

    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
    çļĦç«ŀäºī
    -0.29
    apo
    -0.28
     opposing
    -0.27
     startup
    -0.26
    oy
    -0.26
    ç«ŀäºī对æīĭ
    -0.25
    startup
    -0.25
     Scheduled
    -0.25
    龸çİĭ
    -0.25
     competitor
    -0.24
    POSITIVE LOGITS
    ãģĮãĤī
    0.28
    åİŁåĪĻ
    0.28
    æĦıæĢĿ
    0.27
    æѤæĸĩ
    0.26
     shred
    0.26
    #!
    0.24
    第ä¸īèĬĤ
    0.24
    æľĢåIJİ
    0.24
    rm
    0.24
    ionale
    0.23
    Activations Density 23.549%

    No Known Activations