© 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. 12051
    Prev
    Next
    INDEX
    Explanations

    German sentence connectors

    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
    schirm
    -0.07
    croft
    -0.07
    æĪijå°±ä¼ļ
    -0.07
    æĺ¯ä»¶
    -0.07
    áne
    -0.07
    าà¸ĩ
    -0.07
     اÛĮÙĨÚ©Ùĩ
    -0.07
    deren
    -0.07
    请åijĬçŁ¥
    -0.06
     fosser
    -0.06
    POSITIVE LOGITS
     moreover
    0.13
     infatti
    0.12
     furthermore
    0.12
     therefore
    0.12
    nt
    0.11
     indeed
    0.11
     meanwhile
    0.11
     bowiem
    0.10
     also
    0.10
     nevertheless
    0.10
    Activations Density 0.091%

    No Known Activations