© 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. 5137
    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
    好çļĦ
    -0.25
    象å¾ģ
    -0.25
    artz
    -0.24
     Bail
    -0.23
    raphic
    -0.23
    ç¥ľ
    -0.23
    Fantastic
    -0.22
    atic
    -0.22
    ç»ĵçŁ³
    -0.22
    ouflage
    -0.21
    POSITIVE LOGITS
    ãĤ¬ãĥ¼
    0.24
     beg
    0.23
    ject
    0.23
     enh
    0.23
     заÑĢ
    0.23
     disemb
    0.22
    ixo
    0.22
    itor
    0.22
    yah
    0.22
    è´§
    0.22
    Activations Density 0.138%

    No Known Activations

    This feature has no known activations.