© 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. 37491
    Prev
    Next
    INDEX
    Explanations

    hypothesis and null

    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
    足迹
    -0.09
    ilien
    -0.08
    çļĦäºĭåĦ¿
    -0.08
    huizen
    -0.08
     اÙĨد
    -0.08
    orme
    -0.08
    ä¸Ĭè¿°äºĭå®ŀ
    -0.08
    cioni
    -0.08
     exemp
    -0.08
    cene
    -0.07
    POSITIVE LOGITS
     wording
    0.08
     sets
    0.07
    umat
    0.07
     Sets
    0.07
     formulations
    0.07
    ÙĪÙī
    0.07
    å¤ĩ
    0.07
    bench
    0.07
     pars
    0.07
    设å®ļ
    0.06
    Activations Density 0.001%

    No Known Activations