© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    lack

    np_max-act · gemini-2.0-flash
    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
    EVER
    -0.27
    already
    -0.26
    ä»ĸå·²ç»ı
    -0.26
    tons
    -0.26
    Already
    -0.25
     viên
    -0.25
    大éĩı
    -0.25
     Already
    -0.24
     parasites
    -0.24
    å·¦
    -0.23
    POSITIVE LOGITS
     seperate
    0.29
     separate
    0.28
     qualify
    0.27
    vised
    0.26
    ihu
    0.26
    ::~
    0.25
     quality
    0.25
     Nikola
    0.24
     tsl
    0.24
     elementary
    0.24
    Activations Density 0.031%

    No Known Activations