© 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. 6388
    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
    AH
    -0.26
    漫
    -0.26
    åģľæ»ŀ
    -0.26
     amen
    -0.26
    伪
    -0.25
    Aws
    -0.25
    滹
    -0.24
    æĭ¿åĪ°
    -0.24
    IR
    -0.24
    åĢĴæĺ¯
    -0.24
    POSITIVE LOGITS
    anine
    0.28
    åĴĮæĶ¯æĮģ
    0.25
    åķĨéĩı
    0.25
    abin
    0.25
    çĤ¯
    0.24
    zion
    0.24
    	controller
    0.24
    lyph
    0.24
    rames
    0.23
    æľĽåİ»
    0.23
    Activations Density 5.398%

    No Known Activations

    This feature has no known activations.