© 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. 64741
    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
    æīĵ
    -0.25
    æīĵäºĨ
    -0.24
    æīĵåĩº
    -0.24
    éĤ¸
    -0.24
    balls
    -0.24
    éĴŃ
    -0.24
     Det
    -0.23
    ıntı
    -0.23
    itors
    -0.23
     popular
    -0.23
    POSITIVE LOGITS
    亿åħĥ以ä¸Ĭ
    0.30
     comb
    0.26
    WA
    0.26
    ilig
    0.25
     положиÑĤелÑĮн
    0.24
    驺
    0.24
    ObjectContext
    0.24
    ograd
    0.24
    ukt
    0.23
    edd
    0.23
    Activations Density 33.052%

    No Known Activations

    This feature has no known activations.