© 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. 130814
    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
    ODY
    -0.25
    ACHI
    -0.25
    ibo
    -0.25
    ospital
    -0.24
    licated
    -0.24
    OPLE
    -0.23
     Worth
    -0.23
    dictions
    -0.23
    pees
    -0.23
    inki
    -0.23
    POSITIVE LOGITS
    æĴº
    0.27
    Hur
    0.26
    nite
    0.26
    verse
    0.26
     elems
    0.25
     lame
    0.24
    estone
    0.24
    .effects
    0.24
    /effects
    0.24
    .addHandler
    0.23
    Activations Density 11.980%

    No Known Activations

    This feature has no known activations.