© 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. 108646
    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
    Negative Logits
    iera
    -0.29
    raud
    -0.28
    è¾Ļ
    -0.27
    ç§ī
    -0.27
    à¹Ģà¸Ħย
    -0.25
    Chance
    -0.24
    herited
    -0.24
    Advertisements
    -0.24
     mates
    -0.24
     Desire
    -0.23
    POSITIVE LOGITS
    ograd
    0.28
    ä½łéľĢè¦ģ
    0.28
     shar
    0.27
    ä¹Łä¸įè¦ģ
    0.26
    ä½łåı¯ä»¥
    0.26
     pari
    0.25
    ün
    0.25
    令
    0.24
    UNCH
    0.24
    ä¹Łè¦ģ
    0.23
    Activations Density 15.050%

    No Known Activations

    This feature has no known activations.