© 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. 58950
    Prev
    Next
    INDEX
    Explanations

    surveillance and diagnostic measurement

    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
    agus
    -0.08
    çģ«çĥŃçļĦ
    -0.07
    arrow
    -0.07
    óg
    -0.07
    Ỽ
    -0.07
    ger
    -0.07
    绣çŃ¹æİ¨è¿Ľ
    -0.07
     WebDriver
    -0.07
    endas
    -0.07
    pers
    -0.07
    POSITIVE LOGITS
     diagnostic
    0.11
    çĽijè§Ĩ
    0.10
     surveillance
    0.09
     monitoring
    0.09
     diagnostics
    0.09
    è¯ĬæĸŃ
    0.09
     diagnost
    0.09
    iagnostics
    0.08
     Diagnost
    0.08
    çĽijæµĭ
    0.08
    Activations Density 0.705%

    No Known Activations