© 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. 88548
    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
    å¨ģ
    -0.26
     incarn
    -0.26
    åĨ¥
    -0.26
     trips
    -0.25
    utherford
    -0.25
    enefit
    -0.24
    åħ¨æł¡
    -0.24
     casc
    -0.24
    uestas
    -0.24
    alar
    -0.24
    POSITIVE LOGITS
     Kore
    0.27
    å¼ı
    0.25
    лик
    0.25
     bulls
    0.25
    å¹´åIJİ
    0.25
    å·¥ç¨ĭ建设
    0.25
     (~(
    0.24
    ile
    0.24
    çĺ¸
    0.24
    ä»ĸæĺ¯ä¸Ģ个
    0.24
    Activations Density 5.194%

    No Known Activations

    This feature has no known activations.