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. 46028
    Prev
    Next
    INDEX
    Explanations

    runtime

    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
     Jude
    -0.28
    erland
    -0.27
     paints
    -0.26
    ewis
    -0.26
    emade
    -0.25
    ence
    -0.25
    æ°Ķ象
    -0.24
    lıģa
    -0.24
     Russo
    -0.24
    伸åĩº
    -0.24
    POSITIVE LOGITS
     filter
    0.28
    滤
    0.26
    filter
    0.25
    .vo
    0.25
     membership
    0.25
    dr
    0.24
    AtPath
    0.24
    	filter
    0.24
     Filter
    0.24
    $filter
    0.24
    Activations Density 0.017%

    No Known Activations