© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129591
    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
    æŃ£éĿ¢
    -0.27
     millennium
    -0.27
     Advance
    -0.27
     Sight
    -0.26
     permitted
    -0.25
     Laser
    -0.25
     Life
    -0.25
     default
    -0.24
    ivariate
    -0.24
     organ
    -0.24
    POSITIVE LOGITS
    æijĶ
    0.28
    åºĶæĢ¥ç®¡çIJĨ
    0.28
    wick
    0.27
    .edu
    0.26
    ugin
    0.25
    riad
    0.25
    PAGE
    0.25
    æĭ
    0.24
    ograd
    0.24
    ards
    0.23
    Activations Density 50.996%

    No Known Activations

    This feature has no known activations.