© 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. 129873
    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
     dow
    -0.28
    Au
    -0.27
    延
    -0.27
     vn
    -0.26
    å¾Īæ¼Ĥ亮
    -0.26
     Au
    -0.25
     decent
    -0.25
    ç²
    -0.24
    isión
    -0.24
     reluct
    -0.23
    POSITIVE LOGITS
     materially
    0.27
    epad
    0.25
    vals
    0.25
     اÙĦعربÙĬ
    0.23
    iffs
    0.23
    人åĿĩ
    0.23
     precedent
    0.23
     WTF
    0.23
    åįģä¸ī
    0.23
    ä½ĵ系建设
    0.23
    Activations Density 0.059%

    No Known Activations

    This feature has no known activations.