© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7272
    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
    ICODE
    -0.25
    åĬŁè¯¾
    -0.25
    pmat
    -0.24
    úng
    -0.24
    PLY
    -0.24
    appable
    -0.23
    å¦ĤæľŁ
    -0.23
    _recovery
    -0.23
    Sz
    -0.23
     PendingIntent
    -0.23
    POSITIVE LOGITS
    sburg
    0.28
    aphael
    0.24
    åĪ¶è£ģ
    0.24
    /lab
    0.24
    çIJĨæĥ³
    0.24
    裸
    0.23
    ="#">↵
    0.23
     cach
    0.23
     Surge
    0.23
    llib
    0.23
    Activations Density 0.253%

    No Known Activations

    This feature has no known activations.