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. 1
    Prev
    Next
    INDEX
    Explanations

    Formal documents/titles

    np_max-act · gemini-2.0-flash

    prefix-based temporal markers indicating something occurs before or after an event (often in hyphenated forms).

    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
    ucha
    -0.27
    issance
    -0.25
     TSRMLS
    -0.25
    inaire
    -0.24
    ÑģÑĤоÑı
    -0.24
    ORIA
    -0.24
     Mell
    -0.24
    .reload
    -0.24
    writes
    -0.23
     Lumpur
    -0.23
    POSITIVE LOGITS
    æ³ķå®ļ
    0.27
     condu
    0.24
    å¥ĭæĪĺ
    0.24
    宪æ³ķ
    0.23
    -Con
    0.23
    éŀ®
    0.23
    emies
    0.23
    ophon
    0.23
    :UI
    0.23
    acci
    0.23
    Activations Density 0.003%

    No Known Activations