© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89441
    Prev
    Next
    INDEX
    Explanations

    Internet articles/questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ļä¸Ĭ
    -0.28
    .semantic
    -0.26
     hits
    -0.26
    anus
    -0.26
    .nih
    -0.25
     возмож
    -0.25
    ose
    -0.24
    åıĸåĨ³äºİ
    -0.24
    æĭĪ
    -0.24
     ngữ
    -0.23
    POSITIVE LOGITS
    ä¸į说
    0.30
    第åįģ
    0.29
    第ä¸ī个
    0.29
    ellan
    0.27
    bst
    0.26
    ãĤ
    0.25
    åįĹåĮĹ
    0.24
    asmus
    0.24
    çī©ä»·
    0.24
    eters
    0.24
    Activations Density 26.724%

    No Known Activations