© 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. 3640
    Prev
    Next
    INDEX
    Explanations

    AES encryption

    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
    oque
    -0.07
    нала
    -0.06
    enant
    -0.06
     Fora
    -0.06
    lasting
    -0.06
    åĺĺ
    -0.06
    ä¹ĭå®Ŀ
    -0.06
    èIJ½èIJ½
    -0.06
    é¢Ŀ
    -0.06
    æ§Ľ
    -0.06
    POSITIVE LOGITS
     "../../../
    0.07
    ÙĪاØŃ
    0.07
    ÙĪبات
    0.07
     classific
    0.07
    itek
    0.07
    hound
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    رÙĪع
    0.07
    åıijèªĵ
    0.07
    haf
    0.07
    Activations Density 0.002%

    No Known Activations