© 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. 16287
    Prev
    Next
    INDEX
    Explanations

    culture and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     maiden
    -0.07
    ↵
    -0.07
    -0.07
     E
    -0.06
    -
    -0.06
    æĮīè¦ģæ±Ĥ
    -0.06
    ä¸ĢçĶŁ
    -0.06
     miraculous
    -0.06
     ordinarily
    -0.06
     AI
    -0.06
    POSITIVE LOGITS
    èĪ¶
    0.10
    ç²ĭ
    0.10
    æ¶Īè²»
    0.10
    å¸Ńåį·
    0.10
    çĶŁæ´»æĸ¹å¼ı
    0.09
     Bagno
    0.09
    celet
    0.09
     거리
    0.09
     lifestyle
    0.09
     popularity
    0.09
    Activations Density 0.302%

    No Known Activations