© 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. 26637
    Prev
    Next
    INDEX
    Explanations

    bus, cars, jeans, Walmart, bacon

    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
    irts
    -0.09
    åľ¨åŃ¦ä¹łä¸Ĭ
    -0.08
    ç²Ĺæļ´
    -0.08
    çĶŁæ´»ä¸Ĭ
    -0.07
    åıĬè¦ģæ±Ĥ
    -0.07
    æľīç¦ı
    -0.07
    çī©åĵģ
    -0.07
    ares
    -0.07
    irt
    -0.07
    èĢ³çĽ®
    -0.07
    POSITIVE LOGITS
    æĪĸæĺ¯
    0.09
     magari
    0.08
    æĬijæĪĸ
    0.08
    ä»Ģä¹ĪçļĦ
    0.07
    贯彻èIJ½å®ŀ
    0.07
     misalnya
    0.07
     ÙģÙĦا
    0.07
    æĪĸèĢħåħ¶ä»ĸ
    0.07
     blinking
    0.07
    大æ±ī
    0.07
    Activations Density 1.035%

    No Known Activations