© 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. 63294
    Prev
    Next
    INDEX
    Explanations

    URLs ending in .php or /

    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
    ought
    -0.07
     setUp
    -0.07
    új
    -0.07
    tring
    -0.07
    微信æī«ä¸Ģæī«
    -0.06
    udar
    -0.06
    çĶ¨å¿ĥåİ»
    -0.06
     fixture
    -0.06
    åħ¬åı¸æݨèįIJ
    -0.06
    æĬĬå·¥ä½ľ
    -0.06
    POSITIVE LOGITS
    æѦç¥ŀ
    0.08
    巨人
    0.08
     Accessed
    0.07
    èķĥ
    0.07
    yv
    0.07
    ikian
    0.07
    -mode
    0.07
    å½¢
    0.06
    页éĿ¢çļĦ
    0.06
    ItemId
    0.06
    Activations Density 0.267%

    No Known Activations