© 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. 9214
    Prev
    Next
    INDEX
    Explanations

    starting a career or relationship

    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
    è¿Ļåı«
    -0.07
    çIJ¦
    -0.07
     Nobel
    -0.07
     exponentially
    -0.07
    æīįä¸įä¼ļ
    -0.07
     billions
    -0.07
    èݺ
    -0.07
    æĺĤ
    -0.07
    åıĪæĢķ
    -0.07
     risks
    -0.07
    POSITIVE LOGITS
     reportedly
    0.14
     unspecified
    0.09
    æį®æĬ¥éģĵ
    0.09
    ä¸įä¹ı
    0.08
    æį®è¯´
    0.08
    æį®
    0.08
     undisclosed
    0.08
     bastante
    0.08
    ][]
    0.08
    ä¸įå°ijçļĦ
    0.08
    Activations Density 0.160%

    No Known Activations