© 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. 23-TRANSCODER-HP
    7. 163018
    Prev
    Next
    INDEX
    Explanations

    dates, times, and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¿Ŀ驾
    -0.27
    andon
    -0.26
    æľīæĽ´å¤ļçļĦ
    -0.24
    Repositories
    -0.23
    aigned
    -0.23
    ä¸Ģæīĭ
    -0.23
    UIButton
    -0.23
    ä¸Ģ大æī¹
    -0.23
    iona
    -0.22
     Sundays
    -0.22
    POSITIVE LOGITS
    æľªç»ıæİĪæĿĥ
    0.26
    asks
    0.24
     Props
    0.24
    acks
    0.23
     lượt
    0.23
    0.23
     ↵
    0.23
    alem
    0.23
     att
    0.23
    æ°´æ³µ
    0.23
    Activations Density 0.003%

    No Known Activations