© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ally/-ically

    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
    aisu
    -0.10
    ness
    -0.09
    åŃ¦ä»¥èĩ´
    -0.08
    å¸ĮæľĽå¯¹æĤ¨
    -0.08
    printStats
    -0.07
    aiset
    -0.07
    串
    -0.07
    intang
    -0.07
    缴æİ¥æĪĸ
    -0.07
    enswürd
    -0.07
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.12
    åĴĮæĬĢæľ¯
    0.11
    åĴĮç»ıæµİ
    0.10
    åĴĮæ³ķå¾ĭ
    0.10
     maupun
    0.10
    åĴĮå¿ĥçIJĨ
    0.10
    ãĢģ
    0.09
     and
    0.09
    åĴĮ管çIJĨ
    0.09
    åĴĮæĶ¿æ²»
    0.09
    Activations Density 0.189%

    No Known Activations