© 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. 19-TRANSCODER-HP
    7. 4906
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iked
    -0.29
    iken
    -0.28
     establishing
    -0.26
    æľīæīĢ
    -0.25
    itational
    -0.25
    æĸ§
    -0.25
     poisoned
    -0.24
    ital
    -0.24
    eps
    -0.24
     Presence
    -0.24
    POSITIVE LOGITS
     Nimbus
    0.31
    æŃ¥æŃ¥
    0.30
    fé
    0.27
    umo
    0.27
    ARIO
    0.26
    ä¸įåIJĮç±»åŀĭ
    0.26
    室å¤ĸ
    0.26
     advantage
    0.26
    å¯Ĵ
    0.25
    anas
    0.25
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.