© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59973
    Prev
    Next
    INDEX
    Explanations

    realm

    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
    Negative Logits
    꽤
    -0.08
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.08
    stra
    -0.08
    sWith
    -0.08
    drv
    -0.08
    amous
    -0.08
    ziej
    -0.08
    shire
    -0.08
    à¨Ĩ
    -0.08
    å¾ĢæľŁç²¾å½©
    -0.08
    POSITIVE LOGITS
    å±ĤéĿ¢
    0.07
    å±ĤéĿ¢çļĦ
    0.07
    å±Ĥ次çļĦ
    0.07
    ãģªãģı
    0.07
    檸
    0.07
    ÙĬÙĨ
    0.07
    èĢĥéĩı
    0.06
    ìĦł
    0.06
    °
    0.06
    oldt
    0.06
    Activations Density 0.001%

    No Known Activations