© 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. 5029
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    æŀľ
    -0.23
    abad
    -0.22
    çĭ¬
    -0.21
    als
    -0.20
    æŀľæłij
    -0.20
    ilian
    -0.20
    inea
    -0.19
    udu
    -0.19
    atar
    -0.19
    uh
    -0.19
    POSITIVE LOGITS
    åīľ
    0.22
    ivet
    0.21
    æİĺ
    0.21
    ivant
    0.20
    TTY
    0.19
    带æĿ¥æĽ´å¤ļ
    0.19
    .Modules
    0.19
    มวล
    0.19
    åĽłä¸ºå®ĥ
    0.18
    åŃ¦ä¹łæĪIJ绩
    0.18
    Activations Density 0.035%

    No Known Activations