© 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. 4998
    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
     javafx
    -0.28
    velle
    -0.26
    åħ¥å¸Ĥ
    -0.26
    丼æŀĹ
    -0.26
    é¢Ħå®ļ
    -0.26
    пиÑģание
    -0.25
    	Description
    -0.25
     Äijá»ĩ
    -0.25
    (Optional
    -0.24
    иÑĤеÑĤ
    -0.23
    POSITIVE LOGITS
    acho
    0.28
    æĮĸæİĺ
    0.28
    ourage
    0.27
    weak
    0.26
    å·§å¦Ļ
    0.26
    ä¸įæĸŃ
    0.26
    åħħåĪĨ
    0.25
    天èµĭ
    0.25
    åħħåĪĨåĪ©çĶ¨
    0.25
    rots
    0.24
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.