© 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. 44474
    Prev
    Next
    INDEX
    Explanations

    butterfly or moth

    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
     toe
    -0.08
    æľĶ
    -0.07
    nis
    -0.07
    åĨ½
    -0.07
    imb
    -0.07
    imbra
    -0.07
    æ©
    -0.07
    éĿ´
    -0.07
    æĭīå¾·
    -0.07
    heel
    -0.06
    POSITIVE LOGITS
    èĽ¹
    0.10
    ç¹Ķ
    0.09
     ÑĪелко
    0.09
    纨
    0.09
     butterflies
    0.09
     butterfly
    0.09
     bÆ°á»Ľ
    0.09
     moth
    0.09
     Butterfly
    0.09
    ä¸Ŀ绸
    0.09
    Activations Density 0.089%

    No Known Activations