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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14941
    Prev
    Next
    INDEX
    Explanations

    merely provide background

    np_acts-logits-general · gemini-2.5-flash-lite

    introductory or framing language in technical and academic documents, particularly statements about background information, requirements, or the purpose of research.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "**
    -0.10
     **"
    -0.09
     fiance
    -0.09
    ï¼ļ"
    -0.09
    为äºĨæĽ´å¥½çļĦ
    -0.09
     Ebay
    -0.08
    'er
    -0.08
    "s
    -0.08
     ****
    -0.08
    -lang
    -0.08
    POSITIVE LOGITS
    âĢij
    0.18
      ↵↵
    0.12
    âĢ
    0.11
      ↵
    0.10
    —
    0.09
    —or
    0.09
    —including
    0.09
     markedly
    0.08
    âĤĤ
    0.08
    —from
    0.08
    Activations Density 0.274%

    No Known Activations