© 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. 142760
    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
    HELL
    -0.26
    è¦ģåıĬæŶ
    -0.26
    antly
    -0.26
     FB
    -0.26
    abad
    -0.26
    ç³»åĪĹ产åĵģ
    -0.26
    ier
    -0.25
    åı¶åŃIJ
    -0.25
    å¸Ĥåİ¿
    -0.25
    åı¶
    -0.25
    POSITIVE LOGITS
     guessed
    0.26
    ç²īæľ«
    0.24
    mut
    0.24
    åı¯æݧ
    0.24
    myp
    0.24
    .Executor
    0.24
    èĸª
    0.23
    pow
    0.23
    aji
    0.23
    åįĹéĿŀ
    0.23
    Activations Density 43.382%

    No Known Activations

    This feature has no known activations.