© 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. 14402
    Prev
    Next
    INDEX
    Explanations

    award or citation number

    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
    Enumerable
    -0.07
    <tool_response>
    -0.07
     RED
    -0.07
    漫
    -0.06
    ynd
    -0.06
    ç´«
    -0.06
    ÐŁÐŀ
    -0.06
    ä»Ĭ天
    -0.06
    éĤ¦
    -0.06
    令
    -0.06
    POSITIVE LOGITS
    è¡ĮåĬ¨ä¸Ĭ
    0.08
    aksa
    0.08
    ustru
    0.07
     otherwise
    0.07
    èĢĮèµ°
    0.07
    à¹Ĥว
    0.07
    epro
    0.07
    osg
    0.07
    åİ»çİ©
    0.07
    åIJ¦åĪĻä¼ļ
    0.07
    Activations Density 0.021%

    No Known Activations