© 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. 29392
    Prev
    Next
    INDEX
    Explanations

    ionic materials and electrolytes

    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
    ertools
    -0.08
    åĩºéģĵ
    -0.07
    å¯Ĥ
    -0.07
    æŀļ举
    -0.07
    åıĤèĢĥä»·åĢ¼
    -0.07
    Visibility
    -0.07
    åıįå¼¹
    -0.07
    èĪį
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    ersp
    -0.07
    POSITIVE LOGITS
    两边çļĦ
    0.09
    çĶµè§£è´¨
    0.08
    åIJĦåı¸
    0.08
    éļĶå¼Ģ
    0.08
     inter
    0.07
     replen
    0.07
     connecting
    0.07
    uddy
    0.07
     supplying
    0.07
    åĴĮåIJĦ
    0.07
    Activations Density 0.006%

    No Known Activations