© 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. 47844
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and symbols

    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
    äºĨèĩªå·±çļĦ
    -0.08
    athing
    -0.07
    amber
    -0.07
    erson
    -0.07
    adders
    -0.07
    lah
    -0.07
    alytics
    -0.07
    naver
    -0.07
    ÙĬات
    -0.06
    Someone
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩ
    0.09
    éĩĩçĶ¨
    0.08
    éĢļè¿ĩåIJİ
    0.08
    æł¹æį®
    0.08
    åħ¶ä¸»è¦ģ
    0.07
    otype
    0.07
    èĢĥèĻijåĪ°
    0.07
    êµ°ìļĶ
    0.07
    ä¾Ŀæį®
    0.07
    åį³ä½¿
    0.07
    Activations Density 0.001%

    No Known Activations