© 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. 62428
    Prev
    Next
    INDEX
    Explanations

    buildings and rooms

    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
    è¸ıéĿĴ
    -0.08
    ertz
    -0.08
     cities
    -0.07
    ürk
    -0.07
    cities
    -0.07
    ä¸įåĬł
    -0.07
    è¥
    -0.07
    Cities
    -0.06
     highways
    -0.06
     Playground
    -0.06
    POSITIVE LOGITS
    åĬŁèĥ½çļĦ
    0.11
     annex
    0.10
    åĬŁèĥ½
    0.10
    æ©Łèĥ½ãĤĴ
    0.10
    å¤ļåĬŁèĥ½
    0.09
    åĨħ设
    0.09
    æ©Łèĥ½
    0.09
    æİ¥å¾ħ
    0.09
    ä¸ĢåºĶ俱åħ¨
    0.09
    åĬŁèĥ½æĺ¯
    0.09
    Activations Density 0.818%

    No Known Activations