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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 351
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _BUFF
    -0.26
    éĢŀ
    -0.26
    .HTML
    -0.26
    inalg
    -0.25
    ect
    -0.25
    sector
    -0.25
    wal
    -0.25
     certo
    -0.24
    å°½åĬĽ
    -0.24
    REW
    -0.24
    POSITIVE LOGITS
    mond
    0.28
    amer
    0.27
    arez
    0.27
    æĬĢæľ¯
    0.26
    ITCH
    0.26
    æĬķ
    0.25
    Former
    0.25
    itet
    0.25
    -functions
    0.25
    venes
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.