© 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. 564
    Prev
    Next
    INDEX
    Explanations

    hypo- and hyper- prefixes

    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
    lessly
    -0.07
    anine
    -0.07
    wise
    -0.07
    ç²¾åįİ
    -0.07
    teile
    -0.06
    æ¸Īãģ¿
    -0.06
     wise
    -0.06
    agnostic
    -0.06
    tracks
    -0.06
    less
    -0.06
    POSITIVE LOGITS
    è¡ĢçĹĩ
    0.10
    çĹĩçļĦ
    0.08
    osis
    0.08
    çĹĩæĤ£èĢħ
    0.08
    æĪĸ缺
    0.08
     اÙĦÙĨÙģس
    0.08
     (>
    0.07
    xia
    0.07
    åĴĮä½İ
    0.07
     vero
    0.07
    Activations Density 0.110%

    No Known Activations