© 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. 60649
    Prev
    Next
    INDEX
    Explanations

    currency codes and country names

    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
    DOT
    -0.09
    enam
    -0.08
    åľĪåľĪ
    -0.07
    ä¸ŃæĪIJéķ¿
    -0.07
    zeh
    -0.07
    æĹłæĢ¨
    -0.07
    èĮģ壮æĪIJéķ¿
    -0.07
     previstos
    -0.07
    主
    -0.07
    æīĵçģ«
    -0.07
    POSITIVE LOGITS
    åĴĮèĩªå·±
    0.08
    çĽ¸å¯¹äºİ
    0.07
     relative
    0.07
     Abel
    0.07
     Relative
    0.07
    è¿ijåľ¨
    0.07
    çĽ¸å¯¹çļĦ
    0.07
    Relative
    0.07
     nearby
    0.07
    .adapter
    0.07
    Activations Density 0.021%

    No Known Activations