© 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. 161953
    Prev
    Next
    INDEX
    Explanations

    email-related content/code

    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
    ixe
    -0.25
    ç°ł
    -0.24
    åijĺ
    -0.24
    ä¸įåĩºæĿ¥
    -0.24
    umann
    -0.24
    æ¼Ĥæµģ
    -0.24
    èµ°å»Ĭ
    -0.24
     FAQs
    -0.23
    fadeOut
    -0.23
    ivot
    -0.23
    POSITIVE LOGITS
    compressed
    0.25
    åĭī
    0.25
    omat
    0.25
    æĹłåı¯
    0.24
     clam
    0.24
    .getClassName
    0.24
    (optional
    0.23
    寥
    0.23
    ä¹ĭ称
    0.23
     uneven
    0.23
    Activations Density 0.004%

    No Known Activations