© 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. 5047
    Prev
    Next
    INDEX
    Explanations

    Locations, borders, boundaries

    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
    ä¼ļè®®ä¸Ĭ
    -0.33
     Meeting
    -0.32
     meetings
    -0.31
     meeting
    -0.31
     Meetings
    -0.29
    åı¬å¼Ģ
    -0.28
    ä¼ļ议室
    -0.28
     meet
    -0.27
    座è°Īä¼ļä¸Ĭ
    -0.27
    ä¼ļè®®
    -0.27
    POSITIVE LOGITS
     ::↵
    0.27
    ancies
    0.27
    褶
    0.26
    `),↵
    0.25
    onyms
    0.25
    èĢģåĮĸ
    0.25
    è¿Ļä¹Īå¤ļ
    0.24
    .extensions
    0.23
    onta
    0.23
    è½®æµģ
    0.23
    Activations Density 0.052%

    No Known Activations