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. 7-TRANSCODER-HP
    4. 97731
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bá»Ļ
    -0.30
    å±Ĥ
    -0.26
    å±Ģ
    -0.26
    ä¼łåĩº
    -0.26
    ä¼ł
    -0.25
    Sdk
    -0.24
    ouro
    -0.24
    èħĺ
    -0.24
     infr
    -0.24
    éľĩåĬ¨
    -0.23
    POSITIVE LOGITS
    igi
    0.27
    ogy
    0.25
     Ebola
    0.25
    .ov
    0.25
    ERSION
    0.25
    sembly
    0.24
    reation
    0.24
    åıĹ
    0.24
    ViewById
    0.24
     dạ
    0.24
    Activations Density 0.001%

    No Known Activations