© 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. 7281
    Prev
    Next
    INDEX
    Explanations

    configuration options and properties

    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
    phabet
    -0.07
    ئÙħ
    -0.06
    åĵĪæĭī
    -0.06
    éļIJ
    -0.06
    anze
    -0.06
    .shtml
    -0.06
    ÛĮز
    -0.06
    æģ¨
    -0.06
    çĶŁåij½
    -0.06
     Ñī
    -0.06
    POSITIVE LOGITS
    .publish
    0.07
    æľīæĪij
    0.07
    olling
    0.07
    ×Ĺר
    0.07
    åĵģç§įçļĦ
    0.07
    æݥ踵
    0.07
    asset
    0.07
    ersp
    0.07
    olley
    0.07
    qli
    0.07
    Activations Density 0.001%

    No Known Activations