© 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. 129692
    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
    lus
    -0.30
    esch
    -0.25
    (Bundle
    -0.25
    æľ¬è½®
    -0.25
    Around
    -0.25
    被æī§è¡Į
    -0.24
    odem
    -0.24
    (bundle
    -0.23
    plode
    -0.23
     Bust
    -0.23
    POSITIVE LOGITS
     sit
    0.28
    issy
    0.27
    ÙĨس
    0.26
     ног
    0.26
    hq
    0.25
    çIJIJ
    0.25
    èĩ³å°ij
    0.25
    yl
    0.24
    sit
    0.24
    coni
    0.24
    Activations Density 15.498%

    No Known Activations

    This feature has no known activations.