© 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. 59882
    Prev
    Next
    INDEX
    Explanations

    "vs" constructions

    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
    ijin
    -0.07
    æĶ¯ä»ĺç»Ļ
    -0.07
    Äĥng
    -0.07
    /features
    -0.07
    Fee
    -0.06
    fabric
    -0.06
    isma
    -0.06
    answers
    -0.06
    yeti
    -0.06
    comings
    -0.06
    POSITIVE LOGITS
    çļĦæŶåĢĻäºĨ
    0.10
    ä¸Ģ说
    0.09
    ãģĻãĤĭãģ¨ãģĦãģĨ
    0.08
    æĥħåĨµåĪĨæŀIJ
    0.08
     vs
    0.08
    æĥħåĨµæĿ¥çľĭ
    0.08
    vs
    0.08
    -l
    0.08
    áīł
    0.07
    ãĤĴ使ãģ£ãģŁ
    0.07
    Activations Density 0.205%

    No Known Activations