© 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. 62710
    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
    好åIJ§
    -0.26
     competency
    -0.25
    ality
    -0.24
    inality
    -0.24
     competence
    -0.24
    ãģ¼
    -0.24
    iton
    -0.23
     uten
    -0.23
     foss
    -0.23
    ĥģ
    -0.23
    POSITIVE LOGITS
     cele
    0.28
    Æ°á»Łng
    0.27
    otas
    0.27
    ÑĢÑı
    0.26
    ä¼ĺåħĪ
    0.25
    mac
    0.24
    angu
    0.24
    æĭĨ
    0.24
    /terms
    0.23
     Pru
    0.23
    Activations Density 39.097%

    No Known Activations

    This feature has no known activations.