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. 24137
    Prev
    Next
    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash

    phrases indicating research study design and methodology in scientific abstracts (e.g., declarations that a study is of a specific type).

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    aby
    -0.26
    feld
    -0.25
     Dop
    -0.25
    æı¿
    -0.25
    oload
    -0.24
    YP
    -0.24
    atrix
    -0.24
     pulse
    -0.23
    以åIJİ
    -0.23
     cif
    -0.23
    POSITIVE LOGITS
    åīľ
    0.28
    &q
    0.25
    æĹ¶ä»£çļĦ
    0.25
    GMT
    0.24
    objects
    0.23
    orig
    0.23
    æĥ³å¿ħ
    0.23
    -cr
    0.23
    WND
    0.23
     Wal
    0.22
    Activations Density 0.034%

    No Known Activations