© 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. 142385
    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
    æĭ¿åĩºæĿ¥
    -0.28
    inh
    -0.27
    opened
    -0.26
     breath
    -0.26
    idth
    -0.26
     Oro
    -0.25
    åģļä»Ģä¹Ī
    -0.24
    idy
    -0.24
    ulton
    -0.24
    ith
    -0.24
    POSITIVE LOGITS
    æ¯Ķè¾ĥ
    0.26
     Tales
    0.26
    rafted
    0.25
     liar
    0.25
     comparing
    0.25
     cmp
    0.25
    cmp
    0.25
    毵
    0.24
     %[
    0.24
    awk
    0.23
    Activations Density 2.052%

    No Known Activations

    This feature has no known activations.