© 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. 12648
    Prev
    Next
    INDEX
    Explanations

    explaining or describing facts

    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
    è·º
    -0.07
    اÙĦر
    -0.06
    uluk
    -0.06
    irim
    -0.06
    uyen
    -0.06
    ITA
    -0.06
    å´©
    -0.06
    ãģłãģ£ãģ¦
    -0.06
    ë£
    -0.06
     Colombo
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½
    0.09
    åĬłè½½ä¸Ń
    0.09
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    æīĢæľīè¿ĻäºĽ
    0.08
    æĢ»ä¹ĭ
    0.08
    综ä¸ĬæīĢè¿°
    0.08
    è¿ĻäºĽéĹ®é¢ĺ
    0.08
    è¿ĻäºĽåĽłç´ł
    0.08
    综
    0.08
    綾
    0.08
    Activations Density 0.057%

    No Known Activations