© 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. 44282
    Prev
    Next
    INDEX
    Explanations

    "i am" / "i have" / "for example"

    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
    ennes
    -0.06
    emente
    -0.06
     l
    -0.06
     le
    -0.06
    纵使
    -0.06
     daraus
    -0.05
    çıŃ
    -0.05
    ãĤīãģĭ
    -0.05
    对该
    -0.05
    indah
    -0.05
    POSITIVE LOGITS
     ugyanis
    0.14
     totiž
    0.13
     bowiem
    0.11
    ForKey
    0.10
     infatti
    0.10
    ä»Ģä¹Īåij¢
    0.10
     przecież
    0.09
     nämlich
    0.09
     afinal
    0.09
    æ¯ķç«Łæĺ¯
    0.08
    Activations Density 0.083%

    No Known Activations