© 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. 58986
    Prev
    Next
    INDEX
    Explanations

    adjective followed by noun/phrase

    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
    ç¡®åĪĩ
    -0.07
    è¾¾
    -0.07
     pim
    -0.06
     unpublished
    -0.06
     surv
    -0.06
    aviour
    -0.06
     incurred
    -0.06
     untranslated
    -0.06
    ç¡®
    -0.06
    è´©
    -0.06
    POSITIVE LOGITS
    imli
    0.08
    Õ¥Õ½
    0.08
    .sent
    0.08
    ioned
    0.08
    edig
    0.07
    å¾·åĪ©
    0.07
    AINS
    0.07
    IVI
    0.07
     responseObject
    0.07
    )__
    0.07
    Activations Density 0.008%

    No Known Activations