© 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. 46628
    Prev
    Next
    INDEX
    Explanations

    Bragg soldier

    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
    彩
    -0.07
    Į¨
    -0.07
    ä¸ĢåĽ¢
    -0.07
    纷åijĪ
    -0.07
    usern
    -0.07
    ezza
    -0.07
     studios
    -0.07
    纯
    -0.06
     unlink
    -0.06
    çµ²
    -0.06
    POSITIVE LOGITS
     odd
    0.08
    å¥ĩ
    0.08
    æĮīçħ§è§Ħå®ļ
    0.08
     summed
    0.08
    ẩm
    0.07
    odd
    0.07
    è¡Įä¹ĭ
    0.07
    æľªæĮīè§Ħå®ļ
    0.07
    éŃĶå¹»
    0.07
    -addons
    0.07
    Activations Density 0.003%

    No Known Activations