© 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. 64620
    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
     Coverage
    -0.26
     Twilight
    -0.26
    .ft
    -0.24
    /mock
    -0.24
     twists
    -0.24
    uki
    -0.24
     coverage
    -0.24
    yne
    -0.23
    коÑģ
    -0.23
     qualifying
    -0.23
    POSITIVE LOGITS
     unfit
    0.26
     immediately
    0.26
    æĬ«
    0.25
     Present
    0.25
     unwilling
    0.24
    æĹ¥æĬ¥
    0.24
    çĮ®
    0.24
    vet
    0.24
    ieber
    0.23
    èĦ±
    0.23
    Activations Density 2.247%

    No Known Activations

    This feature has no known activations.