© 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. 7956
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ï½ŀ↵↵
    -0.26
    继ç»Ńä¿ĿæĮģ
    -0.26
    å¿ĥæĦı
    -0.26
    .↵↵
    -0.25
    cheon
    -0.25
    ä¸įéĢĤåIJĪ
    -0.24
    éĻª
    -0.24
    -ever
    -0.24
    -holder
    -0.24
    ãģĶãģĸãģĦãģ¾ãģĻ
    -0.24
    POSITIVE LOGITS
    Experts
    0.26
    æĭĤ
    0.25
     cocks
    0.24
     dilig
    0.24
     flexible
    0.23
    rita
    0.23
     Hess
    0.23
    ä½ľçĶ¨
    0.23
     nt
    0.23
    addock
    0.23
    Activations Density 0.010%

    No Known Activations