© 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. 89152
    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
    @testable
    -0.28
     Scores
    -0.27
    uir
    -0.27
     Orig
    -0.26
    éĥ¨å§Ķ
    -0.25
    è¿Ļæł·çļĦè¯Ŀ
    -0.25
    座
    -0.24
     scores
    -0.24
    Toy
    -0.24
    loadModel
    -0.23
    POSITIVE LOGITS
     Burl
    0.29
    nes
    0.29
    åħ¨çľģ
    0.26
     uns
    0.25
    æľ¬ç«Ļ
    0.25
    ä¸Ģå®ļæĺ¯
    0.23
     long
    0.23
     Jame
    0.23
    è±¹
    0.23
    uner
    0.23
    Activations Density 0.282%

    No Known Activations

    This feature has no known activations.