© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21260
    Prev
    Next
    INDEX
    Explanations

    software systems

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ContentLoaded
    -0.09
    ilton
    -0.07
    Convertible
    -0.07
    IRQ
    -0.07
    تاÙħ
    -0.06
    /GPL
    -0.06
    å°ģåłµ
    -0.06
    æĸĩ广
    -0.06
    ТЬ
    -0.06
     Palme
    -0.06
    POSITIVE LOGITS
     system
    0.09
    è¿IJè¡ĮæľºåĪ¶
    0.08
    ystem
    0.08
    åIJİåı°
    0.08
    system
    0.08
     capable
    0.08
    ระà¸ļà¸ļ
    0.08
    ullo
    0.07
    ç³»ç»Ł
    0.07
    ÏĥÏĦή
    0.07
    Activations Density 0.415%

    No Known Activations