© 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. 30-TRANSCODER-HP
    7. 96069
    Prev
    Next
    INDEX
    Explanations

    Timeout

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¼ĸè¾ij
    -0.48
    ä½ľèĢħ
    -0.47
    æĿ¥æºIJ
    -0.45
     Tags
    -0.43
    åİŁæĸĩ
    -0.43
     tag
    -0.42
    责任ç¼ĸè¾ij
    -0.42
    è¿Ļç¯ĩæĸĩç«ł
    -0.41
     article
    -0.41
    æĸĩç«łæĿ¥æºIJ
    -0.41
    POSITIVE LOGITS
    ures
    0.27
    à¹īา
    0.25
    .Comparator
    0.25
    çIJĨæĻº
    0.24
    agna
    0.24
     uniforms
    0.23
    меÑĤÑĢ
    0.23
    ierarchy
    0.23
    /Gate
    0.23
    -coordinate
    0.23
    Activations Density 0.895%

    No Known Activations