© 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. 5143
    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
     kir
    -0.29
    olib
    -0.26
    AXB
    -0.25
    ONES
    -0.25
    ложениÑı
    -0.25
     similarly
    -0.24
    ushima
    -0.24
     SAVE
    -0.24
    迹
    -0.24
     ABI
    -0.24
    POSITIVE LOGITS
    ediator
    0.26
    alker
    0.26
    dao
    0.25
    æĮīçħ§
    0.25
    éľĢæ±Ĥ
    0.24
    .Ag
    0.24
    çī©è´¨
    0.24
    ienne
    0.23
    /channel
    0.23
    éĺ¶æ®µæĢ§
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.