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. 53663
    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_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
    lez
    -0.26
    rics
    -0.26
    欢è¿İ
    -0.25
    asons
    -0.25
    eted
    -0.25
    à¸Ńล
    -0.25
    añ
    -0.24
    .Atomic
    -0.24
    zych
    -0.24
    佯
    -0.23
    POSITIVE LOGITS
    Caught
    0.29
    é¢ł
    0.26
    abcdef
    0.24
    ABCDEFGHI
    0.24
     negatively
    0.24
     Orchard
    0.24
    .emf
    0.24
    eps
    0.24
    _ioctl
    0.23
    DrawerToggle
    0.23
    Activations Density 0.025%

    No Known Activations