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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8406
    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
    ashed
    -0.29
    ]>↵
    -0.29
    etr
    -0.27
    ä¸Ńåįİ
    -0.27
    åı°è´¦
    -0.25
    ieron
    -0.25
    çļĦä¿¡æģ¯
    -0.25
    çıŃ
    -0.25
    ued
    -0.25
     Burns
    -0.24
    POSITIVE LOGITS
    就说
    0.30
    æľīæĿ¡ä»¶
    0.26
     gover
    0.26
     voc
    0.25
    èĪĢ
    0.24
    joining
    0.24
     Addition
    0.24
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
    ×Ĺק
    0.24
    £¼
    0.24
    Activations Density 2.253%

    No Known Activations

    This feature has no known activations.