© 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. 22105
    Prev
    Next
    INDEX
    Explanations

    radar system

    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
    ilton
    -0.07
    nam
    -0.07
    åŀĴ
    -0.07
    립
    -0.06
     Jorn
    -0.06
    tw
    -0.06
    icca
    -0.06
    ιÏĥη
    -0.06
    uent
    -0.06
    utori
    -0.06
    POSITIVE LOGITS
    éĽ·è¾¾
    0.11
     radar
    0.11
     Radar
    0.10
    æİ¢æµĭ
    0.09
    ä¾¦å¯Ł
    0.09
     probes
    0.09
    èIJ¨æĸ¯
    0.08
     probing
    0.08
    åĪĨç±»åı·
    0.08
     probe
    0.08
    Activations Density 0.017%

    No Known Activations