© 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. 4-TRANSCODER-HP
    7. 41
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    detect
    -0.27
    datum
    -0.27
     Microwave
    -0.26
     .↵↵↵↵
    -0.26
    .sap
    -0.25
    Occurred
    -0.25
    ï¼ģ↵↵↵↵
    -0.25
    ))^
    -0.25
     Tracks
    -0.24
     moreover
    -0.24
    POSITIVE LOGITS
    athers
    0.29
    iors
    0.28
    æ¯Ķè¾ĥ
    0.27
    olina
    0.25
    igator
    0.25
     geh
    0.25
    -show
    0.24
    compass
    0.24
    继ç»Ń
    0.24
    ä¸ĸçķĮä¸Ĭ
    0.24
    Activations Density 1.888%

    No Known Activations