© 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. 88731
    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
    pot
    -0.27
    otten
    -0.25
    uce
    -0.25
    pgsql
    -0.25
    ources
    -0.24
     Exists
    -0.24
     certains
    -0.24
    iter
    -0.24
    Got
    -0.24
     ldc
    -0.24
    POSITIVE LOGITS
     commenting
    0.28
     comments
    0.27
    ħ§
    0.27
    èĽĽ
    0.27
     reunited
    0.25
    好ä¸į好
    0.25
    è¿Ļæł·çļĦè¯Ŀ
    0.25
    IntArray
    0.24
    ä¼ĺå¼Ĥ
    0.24
     commented
    0.23
    Activations Density 10.071%

    No Known Activations

    This feature has no known activations.