© 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. 35018
    Prev
    Next
    INDEX
    Explanations

    maximal function

    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
    ué
    -0.06
    é¼ĵ
    -0.06
    æļĸ
    -0.06
     china
    -0.06
     fig
    -0.06
    åŃĶ
    -0.06
    æģŃ
    -0.06
     bell
    -0.06
    çŃĴ
    -0.06
    رة
    -0.06
    POSITIVE LOGITS
     caches
    0.09
     Leng
    0.08
     Chains
    0.08
    ynd
    0.08
    å¦Ĥ约
    0.08
    اÙģتÙĩ
    0.08
    weg
    0.08
    ิà¸Ĭ
    0.08
    åĪĿ审
    0.08
    arat
    0.08
    Activations Density 0.001%

    No Known Activations