© 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. 64586
    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
     Câm
    -0.31
    sterol
    -0.28
    [--
    -0.28
    illez
    -0.28
    hiếu
    -0.25
     concentrate
    -0.24
    íĹĢ
    -0.24
     sscanf
    -0.24
    ixa
    -0.24
    æĸ°èģŀ
    -0.24
    POSITIVE LOGITS
    æ°ijæĹıæĸĩåĮĸ
    0.29
    à´¨
    0.28
    河西
    0.27
    à´¦
    0.27
     sw
    0.26
     pathways
    0.26
    da
    0.26
    æģIJæĥ§
    0.25
     axis
    0.25
    landing
    0.25
    Activations Density 22.668%

    No Known Activations

    This feature has no known activations.