© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22864
    Prev
    Next
    INDEX
    Explanations

    integral expressions and formats

    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
    çī¢
    -0.08
    éĻ¤éĿŀ
    -0.07
     Unless
    -0.07
    çļĦ大å°ı
    -0.07
    解åĨ»
    -0.07
    åİŁåĪĻä¸Ĭ
    -0.07
     unas
    -0.07
    ãĥŁãĥĥãĤ¯
    -0.07
    Ont
    -0.07
     nominal
    -0.07
    POSITIVE LOGITS
    cid
    0.07
    æĶ¶æķĽ
    0.07
     Klo
    0.07
     arc
    0.06
    åĴĮåĽ½å®¶
    0.06
     integrate
    0.06
     Tit
    0.06
     Integra
    0.06
     perfil
    0.06
    arc
    0.06
    Activations Density 0.010%

    No Known Activations