© 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. 25819
    Prev
    Next
    INDEX
    Explanations

    Arabian Peninsula and related geopolitics

    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
    éĹ®åĮ»çĶŁ
    -0.07
    .fm
    -0.07
    ths
    -0.07
    á»
    -0.07
    llib
    -0.07
    หมา
    -0.07
    åģİ
    -0.07
    æ±Łæµ·
    -0.07
    äºĮè¿ŀ
    -0.07
    ëįķ
    -0.06
    POSITIVE LOGITS
    Saudi
    0.10
     سعÙĪد
    0.10
     Saudi
    0.10
     arab
    0.09
     Arabia
    0.09
     аÑĢа
    0.08
     Arab
    0.08
     Riyadh
    0.08
    iti
    0.08
    æ²Ļæ¼ł
    0.08
    Activations Density 0.049%

    No Known Activations