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. 30-TRANSCODER-HP
    4. 15097
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ultimate
    -0.25
    å°ıäºİ
    -0.25
     Liberation
    -0.25
    ÑģÑĤавлен
    -0.25
    为空
    -0.25
    (Parcel
    -0.24
    éªŀ
    -0.24
    ÙĬرا
    -0.24
    \Active
    -0.24
     drain
    -0.24
    POSITIVE LOGITS
    两个
    0.35
     towards
    0.33
     close
    0.30
     in
    0.30
     two
    0.29
    ousse
    0.29
     specifically
    0.28
     toward
    0.27
    opus
    0.27
     handic
    0.26
    Activations Density 0.109%

    No Known Activations