© 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. 140784
    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
    ache
    -0.26
    æ·³
    -0.26
    omm
    -0.24
    å¸Ľ
    -0.24
    proto
    -0.23
    ĺìĿ´
    -0.23
     afraid
    -0.22
    éĵ¨
    -0.22
    irma
    -0.22
    åįĥ
    -0.22
    POSITIVE LOGITS
     OrderedDict
    0.27
    æݢ究
    0.26
     orderly
    0.26
    leness
    0.24
    inke
    0.24
    TED
    0.24
     Ups
    0.24
    å°ıåºĹ
    0.23
    unda
    0.23
    icides
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.