© 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. 5099
    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
    åij¨äºĮ
    -0.25
    纤维
    -0.25
    çĶŁéķ¿
    -0.24
    究竣æĺ¯
    -0.24
    WithValue
    -0.24
    è¿IJè¡Į
    -0.23
    apel
    -0.23
     growing
    -0.23
    æľīä¸Ģ次
    -0.23
    åĪ°åºķ
    -0.23
    POSITIVE LOGITS
    emodel
    0.28
    å»·
    0.27
    è·º
    0.27
    -legged
    0.25
    eten
    0.25
    弯
    0.24
     Bry
    0.23
    ç°ª
    0.23
    plr
    0.23
    emat
    0.23
    Activations Density 0.061%

    No Known Activations

    This feature has no known activations.