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. 46394
    Prev
    Next
    INDEX
    Explanations

    and

    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
    æŁ¥æĺİ
    -0.26
    泡
    -0.26
     Peninsula
    -0.26
    çĮĹ
    -0.25
    ä¸įå°ijäºİ
    -0.25
    çϾä½Ļ
    -0.24
    约
    -0.24
    afari
    -0.24
    clidean
    -0.23
    snow
    -0.23
    POSITIVE LOGITS
    okit
    0.29
    uestas
    0.28
     periods
    0.26
    å¼Ħå¾Ĺ
    0.26
    pot
    0.26
     Fourth
    0.25
    ertos
    0.24
    ä¸Ģç«Ļ
    0.24
    abble
    0.24
    anda
    0.24
    Activations Density 0.055%

    No Known Activations