© 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. 44726
    Prev
    Next
    INDEX
    Explanations

    either/or relationships

    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
    ilan
    -0.08
    ,:,:
    -0.08
     곧
    -0.06
    rais
    -0.06
    æ±½
    -0.06
    quilibr
    -0.06
    ibia
    -0.06
    群çļĦ
    -0.06
    .initialize
    -0.06
    setzen
    -0.06
    POSITIVE LOGITS
     either
    0.12
    è¦ģä¹Ī
    0.12
    è¦ģä¹Īæĺ¯
    0.10
    either
    0.10
     EITHER
    0.10
     Either
    0.09
     entweder
    0.09
    Either
    0.09
     либо
    0.08
    æľĢèµ·çłģ
    0.08
    Activations Density 0.009%

    No Known Activations