Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46634
    Prev
    Next
    INDEX
    Explanations

    Scientific or technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meg
    -0.27
    ืà¸Ń
    -0.26
    /platform
    -0.26
    .weights
    -0.25
    POSITION
    -0.25
    oya
    -0.25
    olan
    -0.25
     Indo
    -0.25
    .Sdk
    -0.24
     consent
    -0.24
    POSITIVE LOGITS
     Board
    0.27
    tres
    0.25
    ä¸ľè·¯
    0.25
    ä½Ĩæĺ¯ä»ĸ
    0.25
     Live
    0.24
     '/../
    0.24
     Lottery
    0.23
    learner
    0.23
     live
    0.23
    ernote
    0.23
    Activations Density 0.068%

    No Known Activations