© 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. 6125
    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
    ément
    -0.27
    ç»ıåİĨ
    -0.26
    uren
    -0.26
     seventh
    -0.26
    ug
    -0.25
    åĪĨæķ£
    -0.24
    建议
    -0.24
     digest
    -0.24
    оÑĩки
    -0.24
    ÃŃvel
    -0.24
    POSITIVE LOGITS
    {},
    0.27
    ASI
    0.27
    asl
    0.27
     Casc
    0.27
     sho
    0.26
     shady
    0.25
    æŃ¤é¡¹
    0.24
    zon
    0.24
    icle
    0.24
    lish
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.