© 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. 11008
    Prev
    Next
    INDEX
    Explanations

    android.view or android.widget

    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
    yder
    -0.08
    erop
    -0.07
    ]()
    -0.07
    azor
    -0.07
    /../
    -0.07
    aravel
    -0.07
    urato
    -0.07
    azz
    -0.07
    esterday
    -0.07
    åľ¨èº«è¾¹
    -0.07
    POSITIVE LOGITS
    lien
    0.06
     Gow
    0.06
    YP
    0.06
    æŁļ
    0.06
     FIRST
    0.06
    get
    0.06
    ä¸Ńç§ĭ
    0.06
    empl
    0.06
     pula
    0.05
    out
    0.05
    Activations Density 0.201%

    No Known Activations