© 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. 26619
    Prev
    Next
    INDEX
    Explanations

    method or way

    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
    رÙĬات
    -0.09
    ä¹Łå¹¶éĿŀ
    -0.07
    åľ¨æŃ¤æ¬¡
    -0.07
     statt
    -0.07
    çļĦéĤ£äºĽ
    -0.07
    æľīåĵªäºĽ
    -0.07
    pee
    -0.07
    enje
    -0.07
    imine
    -0.07
    æīįå¾Ĺ以
    -0.07
    POSITIVE LOGITS
    缴æİ¥åľ¨
    0.11
    缴æİ¥çĶ¨
    0.11
     direct
    0.10
    缴æİ¥ä»İ
    0.10
    缴æİ¥
    0.10
    缴æݥ使çĶ¨
    0.10
     directly
    0.10
    ä¼łç»ŁçļĦ
    0.09
    缴æİ¥çļĦ
    0.09
     simply
    0.09
    Activations Density 0.168%

    No Known Activations