© 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. 45012
    Prev
    Next
    INDEX
    Explanations

    less than 0.001", "US-led sanctions", "early intervention may", "law enforcement priorities have shifted"

    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
    adrid
    -0.07
    ä¸Ģç±³
    -0.07
    ude
    -0.07
    rescia
    -0.07
    ümer
    -0.07
    icules
    -0.07
    ä¹Łæĺ¯æľĢ
    -0.07
    neos
    -0.07
    interop
    -0.07
    orme
    -0.07
    POSITIVE LOGITS
    ä¸įæĦ§
    0.08
    ç«Łæĺ¯
    0.08
     apparently
    0.08
    èµ·åĪ°äºĨ
    0.08
    æŀľçĦ¶æĺ¯
    0.08
    æĺ¯å¤ļä¹Ī
    0.08
    ç«Ł
    0.07
    åľ¨å½ĵæŶ
    0.07
    羣æĺ¯ä¸ª
    0.07
    ëįĶëĭĪ
    0.07
    Activations Density 0.125%

    No Known Activations