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. 2-TRANSCODER-HP
    4. 10
    Prev
    Next
    INDEX
    Explanations

    bud

    np_max-act · gemini-2.0-flash

    tokens containing the string “bud,” especially the common plural noun and proper nouns beginning with “Bud-.”

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_2.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.2.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseType
    -0.25
    è¶¾
    -0.25
    AccessType
    -0.25
    åIJĪåĩ»
    -0.25
    perate
    -0.24
    .mozilla
    -0.23
    å¢ĻéĿ¢
    -0.23
    anker
    -0.23
    æİĺ
    -0.23
     MacDonald
    -0.23
    POSITIVE LOGITS
    ä¸ĢåĪĩéĥ½æĺ¯
    0.30
    lines
    0.29
     Biggest
    0.27
    quis
    0.26
     dict
    0.26
    ssc
    0.25
    è¿Ļç§įæĥħåĨµ
    0.24
     favor
    0.24
    :`~
    0.24
     colspan
    0.24
    Activations Density 43.586%

    No Known Activations