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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161785
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ份
    -0.28
    èµı
    -0.28
    æĮĩæłĩ
    -0.26
     interaction
    -0.26
    ä¸į容æĺĵ
    -0.24
    ä¸Ģç¬Ķ
    -0.24
    碼
    -0.24
    æĻĮ
    -0.23
    并ä¸įä¼ļ
    -0.23
    èħ¿
    -0.23
    POSITIVE LOGITS
     wish
    0.26
    itori
    0.25
    enze
    0.24
    æ»ļ
    0.24
     wished
    0.24
    .sdk
    0.23
    _iv
    0.23
    ems
    0.23
    createView
    0.23
    ivic
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.