© 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. 88539
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    */,↵
    -0.28
    */,
    -0.27
    /java
    -0.25
     ByteArrayOutputStream
    -0.24
    ienen
    -0.23
    åľ°ä¸Ń
    -0.23
    aze
    -0.23
     lower
    -0.23
    vtk
    -0.23
     remake
    -0.23
    POSITIVE LOGITS
    并åIJij
    0.27
    ä»Ĭ天
    0.26
    åĽ´
    0.26
    spath
    0.26
    Want
    0.25
    æłĩ
    0.25
    want
    0.24
    inger
    0.24
    talk
    0.24
    today
    0.24
    Activations Density 2.851%

    No Known Activations

    This feature has no known activations.