© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26891
    Prev
    Next
    INDEX
    Explanations

    contacted

    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
    éħī
    -0.08
    chau
    -0.07
    çļĨåı¯
    -0.07
    çļĦæĸ¹æ³ķæĿ¥
    -0.07
    å¹´åīįçļĦ
    -0.07
    èĭ¥å¹²ä¸ª
    -0.07
    éĥ½æľīæīĢ
    -0.06
    ä¹ĥ
    -0.06
    æ°ı
    -0.06
    FullScreen
    -0.06
    POSITIVE LOGITS
     ìľĦíķ´ìĦľëĬĶ
    0.10
     azonban
    0.09
    åħ®
    0.09
     ëĶ°ë¥´ë©´
    0.09
     inilah
    0.09
     ||=
    0.09
     ugyanis
    0.09
    ä¸įåIJĮçļĦæĺ¯
    0.09
     infatti
    0.08
     λοι
    0.08
    Activations Density 0.013%

    No Known Activations