© 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. 8317
    Prev
    Next
    INDEX
    Explanations

    object properties and method calls

    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
    ä¸įäºĨå¤ļä¹ħ
    -0.07
    æ±ĤçĶŁåŃĺ
    -0.07
    ,[],
    -0.07
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    -0.07
    /cat
    -0.07
    纳士
    -0.07
    çıĪ
    -0.07
    çĻ¾è®¡
    -0.07
     [][]
    -0.07
    ],$
    -0.07
    POSITIVE LOGITS
    estes
    0.06
    _frontend
    0.06
    aky
    0.06
    OURNAL
    0.06
    astes
    0.06
    ibase
    0.06
    æ´¥
    0.06
     Dise
    0.06
    paces
    0.06
     applauded
    0.06
    Activations Density 0.145%

    No Known Activations