© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49647
    Prev
    Next
    INDEX
    Explanations

    future events and possibilities

    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
     sometimes
    -0.11
    æľĢè¿ijãģ¯
    -0.11
     often
    -0.10
     usually
    -0.10
    æľīæŶ
    -0.10
     parfois
    -0.10
    è¾Ħ
    -0.10
    often
    -0.09
    sometimes
    -0.09
    æľīæŶåĢĻ
    -0.09
    POSITIVE LOGITS
    å±ĬæŶ
    0.21
    åĪ°æŶåĢĻ
    0.19
     someday
    0.18
    è¿Ļå°Ĩ
    0.14
    åĪ°æŶ
    0.14
     Ø®ÙĪاÙĩÙĨد
    0.13
     nanti
    0.12
     future
    0.12
    ä¹Łè®¸ä¼ļ
    0.12
    åľ¨æľªæĿ¥çļĦ
    0.12
    Activations Density 1.003%

    No Known Activations