© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108479
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ´¾
    -0.28
     comparative
    -0.28
     Ngh
    -0.27
     pairwise
    -0.26
    çİĩ为
    -0.26
    ently
    -0.26
    她说
    -0.26
    filer
    -0.25
     simultaneously
    -0.25
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ§
    -0.24
    POSITIVE LOGITS
    åĵģä½į
    0.27
    åĬłçĽŁ
    0.26
    ähl
    0.26
     Dynasty
    0.25
    ori
    0.25
    intent
    0.25
    åĿĩåı¯
    0.25
    ä»ħ代表
    0.25
    ubi
    0.24
    ä¹Łåı¯
    0.24
    Activations Density 2.390%

    No Known Activations

    This feature has no known activations.