© 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. 18542
    Prev
    Next
    INDEX
    Explanations

    real summer this year

    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
    uhl
    -0.09
    apollo
    -0.08
    opan
    -0.08
    czyn
    -0.08
    家æĺ¯
    -0.08
    ì¹Ļ
    -0.07
    ||||
    -0.07
    æīĢ欲
    -0.07
     satélite
    -0.07
     torino
    -0.07
    POSITIVE LOGITS
    onth
    0.08
    åĮº
    0.07
    åīįæıIJ
    0.07
    ãģ©
    0.07
    UnitTest
    0.07
    åĮºåĨħ
    0.07
    dent
    0.06
    ambito
    0.06
    (TestCase
    0.06
    åįĢ
    0.06
    Activations Density 0.004%

    No Known Activations