© 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. 8713
    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
    Authenticate
    -0.28
    è¿Ļæł·çļĦè¯Ŀ
    -0.27
    .tensor
    -0.25
    EmailAddress
    -0.25
    èĢĮçİ°åľ¨
    -0.25
    -kit
    -0.24
    TemplateName
    -0.24
    çļĦæĦ¿æľĽ
    -0.24
     Palestin
    -0.24
    èįª
    -0.24
    POSITIVE LOGITS
    ]{
    0.29
    ä¸Ģç§į
    0.25
    -turn
    0.25
    ]string
    0.25
    åIJIJ
    0.25
     Cost
    0.24
     Chang
    0.24
     cost
    0.24
    åºķ线
    0.24
    åįĹè·¯
    0.24
    Activations Density 0.286%

    No Known Activations