© 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. 58997
    Prev
    Next
    INDEX
    Explanations

    fixed points and coordinates

    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
    åħģ
    -0.07
    æľīçļĦ
    -0.07
    å±±éĩİ
    -0.06
    صÙĬÙĦ
    -0.06
     less
    -0.06
     Rolling
    -0.06
    ToFit
    -0.06
    ehan
    -0.06
    Document
    -0.06
    Meter
    -0.06
    POSITIVE LOGITS
     coordinates
    0.10
    coordinates
    0.09
    åĿIJæłĩ
    0.09
    横åIJij
    0.09
    平顶
    0.08
    ä½įäºİ
    0.08
     coordinate
    0.08
     Coordinates
    0.08
     vertical
    0.08
     location
    0.08
    Activations Density 0.009%

    No Known Activations