© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 10
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    uses of “that” introducing explanatory phrases or relative clauses.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪIJ份
    -0.25
    æīĵçĿĢ
    -0.25
    å¶Ļ
    -0.23
    åĽłä¸ºä»ĸ
    -0.23
    -ended
    -0.23
    ãģ¾ãģ¾
    -0.22
    itti
    -0.22
     stemmed
    -0.22
    æİĴè¡Į
    -0.22
     sake
    -0.22
    POSITIVE LOGITS
     aforementioned
    0.26
     puis
    0.24
    Äħd
    0.24
    个å¤ļ
    0.22
    次ä¼ļè®®
    0.22
    åįģéĩĮ
    0.22
    ness
    0.22
    ../../../
    0.22
     enc
    0.22
     merely
    0.21
    Activations Density 0.592%

    No Known Activations