© 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. 5038
    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
     subject
    -0.27
    æľĽ
    -0.25
     simple
    -0.25
    åİ»çľĭ
    -0.25
    autom
    -0.25
    lookup
    -0.25
    éĤ£ä»½
    -0.24
    èģĮä¸ļæĬĢæľ¯
    -0.24
    มา
    -0.24
     autom
    -0.24
    POSITIVE LOGITS
     "()
    0.28
    reur
    0.27
    erval
    0.27
    åŁ·
    0.26
    WIDTH
    0.26
     Peer
    0.26
    odable
    0.26
    /Foundation
    0.25
     peer
    0.25
     coached
    0.24
    Activations Density 0.346%

    No Known Activations

    This feature has no known activations.