© 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. 4787
    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
    èįª
    -0.27
    èĤ´
    -0.27
    ittal
    -0.26
    æĺ¯è°ģ
    -0.25
    åĵªä¸Ģ个
    -0.24
     qual
    -0.24
    产ä¸ļåįĩ级
    -0.24
     Auditor
    -0.23
    çĭ¸
    -0.23
    æľ¬é¢Ĩ
    -0.23
    POSITIVE LOGITS
    åı°
    0.30
    èĩº
    0.29
     Establishment
    0.26
     ters
    0.24
    ÐĦ
    0.24
    iens
    0.24
     Breast
    0.24
     hand
    0.24
    èĩ³äºİ
    0.23
     plata
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.