© 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. 140730
    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
    ä¸ĢåĪĨ
    -0.29
    DOM
    -0.28
     Hä
    -0.27
     esc
    -0.27
    häuser
    -0.27
    BAT
    -0.26
    _dom
    -0.25
    SEL
    -0.25
     dom
    -0.25
    bat
    -0.24
    POSITIVE LOGITS
    æīĢè°ĵ
    0.24
    gratis
    0.24
    çݯèĬĤ
    0.24
     gere
    0.24
    apos
    0.23
    ierte
    0.23
     Shorts
    0.23
    anut
    0.22
    èµŀåĬ©
    0.22
    destroy
    0.22
    Activations Density 15.941%

    No Known Activations

    This feature has no known activations.