© 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. 27-TRANSCODER-HP
    7. 9239
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and Organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĽĩ
    -0.27
    èł¢
    -0.27
    年以æĿ¥
    -0.27
    以èī²
    -0.26
    åıªä¸įè¿ĩæĺ¯
    -0.25
    åıĸåĨ³äºİ
    -0.25
    åĩºä¼ļ
    -0.25
    à¹Ĥà¸ķ
    -0.24
    ÅŁim
    -0.23
    stras
    -0.23
    POSITIVE LOGITS
    åĵĢ
    0.27
    .Cryptography
    0.23
    .coroutines
    0.23
    mland
    0.23
     predicted
    0.23
    биÑĢ
    0.23
    meno
    0.23
     UIApplication
    0.23
    交èѦ
    0.23
     Zucker
    0.23
    Activations Density 0.008%

    No Known Activations