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. 15411
    Prev
    Next
    INDEX
    Explanations

    "ever" or "never"

    np_max-act · gemini-2.0-flash

    questions or statements about whether something has ever occurred (lifetime experience, including negations like “not at any time”).

    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
    ç¿Ķ
    -0.28
    太
    -0.26
     REPL
    -0.26
    åζå®ļ
    -0.26
    Äħż
    -0.26
    uci
    -0.26
    è°Ĺ
    -0.25
    æĹĹ
    -0.25
    xin
    -0.25
    éĩįä»»
    -0.24
    POSITIVE LOGITS
     sprung
    0.32
    ä¹Łä¸įä¾ĭå¤ĸ
    0.26
    iores
    0.25
    ://"
    0.24
    è¿ĶåĽŀæIJľçĭIJ
    0.24
    _Run
    0.24
    ç¨Ķ
    0.23
     Yus
    0.23
    stakes
    0.23
     vers
    0.23
    Activations Density 0.005%

    No Known Activations