© 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. 4888
    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
     visuals
    -0.27
    æ¹¾
    -0.27
    å¾ĢåIJİ
    -0.26
    essages
    -0.25
     irres
    -0.25
    visual
    -0.25
     assistants
    -0.25
     dum
    -0.24
    åįģéĩĮ
    -0.24
    Licensed
    -0.24
    POSITIVE LOGITS
    α
    0.28
    æ´¾
    0.27
    继
    0.26
    票
    0.25
    pite
    0.25
    åħ±
    0.25
     HomeController
    0.25
     thuis
    0.24
     home
    0.24
    анг
    0.24
    Activations Density 1.174%

    No Known Activations

    This feature has no known activations.