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. 46207
    Prev
    Next
    INDEX
    Explanations

    separators/delimiters

    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
    [@
    -0.28
     unanimously
    -0.28
    :UI
    -0.27
    èĥ½åĬĽå¼º
    -0.27
    å°±è§īå¾Ĺ
    -0.26
    *))
    -0.25
     supers
    -0.24
     dangerously
    -0.24
     Post
    -0.24
     SSL
    -0.24
    POSITIVE LOGITS
    alloca
    0.27
    orman
    0.24
    orrow
    0.24
    ousy
    0.24
     advoc
    0.23
     Poverty
    0.23
    atology
    0.23
     Caucus
    0.23
    .throw
    0.23
     forget
    0.23
    Activations Density 1.405%

    No Known Activations