© 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. 45204
    Prev
    Next
    INDEX
    Explanations

    retirement savings accounts

    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
    èij©
    -0.07
    åıijå¸ĥä¿¡æģ¯
    -0.06
    éĻįä»·
    -0.06
    éłĴ
    -0.06
    asca
    -0.06
     conduct
    -0.06
    å±¥
    -0.06
    èµĶåģ¿
    -0.06
    èIJ¥ä¸ļé¢Ŀ
    -0.06
    üd
    -0.06
    POSITIVE LOGITS
    个人账æĪ·
    0.09
    ç¼´åŃĺ
    0.09
    åĤ¨èĵĦ
    0.09
    åŃĺåħ¥
    0.09
    [opt
    0.08
    -push
    0.08
    åĦ²
    0.08
     deposit
    0.08
     fund
    0.08
    åĤ¨
    0.08
    Activations Density 0.072%

    No Known Activations