© 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. 88766
    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
    andan
    -0.27
    ofil
    -0.26
    临
    -0.26
    è¡Į使
    -0.25
    æłĩçļĦ
    -0.25
    æİ¥
    -0.24
    èĩ¨
    -0.24
    ลà¸Ńย
    -0.24
    éħ¿
    -0.23
    .CreateCommand
    -0.23
    POSITIVE LOGITS
     pip
    0.31
     themselves
    0.28
     Pip
    0.25
     upside
    0.25
    åī©ä½Ļ
    0.25
     Fal
    0.25
     yourselves
    0.24
    Dot
    0.24
    åĽłä¸ºä»ĸ们
    0.24
    ethe
    0.24
    Activations Density 7.610%

    No Known Activations

    This feature has no known activations.