© 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. 6224
    Prev
    Next
    INDEX
    Explanations

    Explanations and justifications

    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
    ivity
    -0.28
     jeopardy
    -0.27
    åŀĽ
    -0.26
    åĨ·åĨ·
    -0.26
    pile
    -0.26
    éĢīæĭ©äºĨ
    -0.26
    Inventory
    -0.25
     mig
    -0.25
    sess
    -0.24
    她说
    -0.24
    POSITIVE LOGITS
     usual
    0.28
    éģĵçIJĨ
    0.27
    fern
    0.26
    ä¸ĢèĪ¬çļĦ
    0.26
     normally
    0.25
    æĺ¯å¦Ĥä½ķ
    0.25
    鼷æĸ¯
    0.24
    æĺ¯æĢİæł·
    0.24
    rikes
    0.23
     Tal
    0.23
    Activations Density 0.013%

    No Known Activations