© 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. 44136
    Prev
    Next
    INDEX
    Explanations

    lubricates and grease

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĭĵå±ķ
    -0.07
    éĻIJåĪ¶æĢ§
    -0.07
    èij©
    -0.07
    æĭ¼æİ¥
    -0.06
     recon
    -0.06
    夷
    -0.06
     apar
    -0.06
    å¡ijå½¢
    -0.06
     Moff
    -0.06
    è¹´
    -0.06
    POSITIVE LOGITS
     lubric
    0.14
    润æ»ij
    0.14
     oil
    0.13
    æ²¹
    0.12
    润æ»ijæ²¹
    0.12
    æ²¹çļĦ
    0.12
    æ²¹èĦĤ
    0.12
     Oil
    0.12
    Oil
    0.11
     Lub
    0.10
    Activations Density 0.043%

    No Known Activations