© 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. 31159
    Prev
    Next
    INDEX
    Explanations

    android attributes and query syntax

    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
    ilah
    -0.08
     ì§
    -0.07
    heets
    -0.07
    eson
    -0.07
    ampo
    -0.07
    mp
    -0.07
    WithData
    -0.07
     компанией
    -0.07
    äºĮè¿ŀ
    -0.07
    æĶ¹ç¼ĸèĩª
    -0.07
    POSITIVE LOGITS
    éľĨ
    0.07
    arrow
    0.07
    arend
    0.07
     popr
    0.07
    ç®Ń
    0.07
    OperationException
    0.07
    ullet
    0.07
    以身
    0.06
    ansom
    0.06
    éĿĻçļĦ
    0.06
    Activations Density 0.032%

    No Known Activations