© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8673
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    ä¹Łå¥½
    -0.31
    enas
    -0.28
    è¿Ļå¼ł
    -0.27
    anas
    -0.26
    ches
    -0.25
    ieres
    -0.25
    okies
    -0.24
    zure
    -0.24
     mans
    -0.24
    ноÑģÑĤÑĮÑİ
    -0.24
    POSITIVE LOGITS
    .addHandler
    0.27
    è´¨
    0.27
    .metric
    0.27
     met
    0.24
    barang
    0.24
    ä¸ĭéĿ¢æĪij们
    0.24
    inaire
    0.24
    è·ª
    0.23
    ouv
    0.23
    åij½
    0.23
    Activations Density 0.853%

    No Known Activations