© 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. 63548
    Prev
    Next
    INDEX
    Explanations

    Numerical comparisons

    np_max-act · gemini-2.0-flash
    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
    atron
    -0.32
    cluded
    -0.30
    redits
    -0.28
    ayout
    -0.26
    Č↵
    -0.25
    ViewById
    -0.24
     verge
    -0.24
    otts
    -0.24
    ä»ĸ们çļĦ
    -0.24
    dÃŃ
    -0.24
    POSITIVE LOGITS
    åıĪ好
    0.31
    AVA
    0.28
    est
    0.27
     reef
    0.27
    EST
    0.27
    çıĬçijļ
    0.27
    YN
    0.26
    orca
    0.25
    èħĭ
    0.25
    ials
    0.24
    Activations Density 3.816%

    No Known Activations