© 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. 48146
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code structure

    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
    çĶŁæ´»ä¸Ĭ
    -0.06
    çĶŁäº§å»ºè®¾åħµåĽ¢
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
     broader
    -0.06
    ä¸İå®ŀéĻħ
    -0.05
    жней
    -0.05
    åľ¨åħ·ä½ĵ
    -0.05
    课åłĤä¸Ĭ
    -0.05
    l
    -0.05
    à§įà¦ŀ
    -0.05
    POSITIVE LOGITS
    à¹Īาà¸Ļ
    0.09
    imir
    0.09
    ignant
    0.08
     nát
    0.08
    शà¥Ģ
    0.08
    ymar
    0.08
    è´¹åĴĮ
    0.08
    ogui
    0.08
    assed
    0.08
    levator
    0.08
    Activations Density 0.149%

    No Known Activations