© 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. 30123
    Prev
    Next
    INDEX
    Explanations

    types of content

    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
    æŁIJäºĽ
    -0.11
    æľīæŶä¼ļ
    -0.08
     sometimes
    -0.08
    æīĢæľīçļĦ
    -0.08
    ä»»ä½ķæŶåĢĻ
    -0.08
     certain
    -0.08
     always
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    æŁIJç§į
    -0.08
    æīĢæľī
    -0.08
    POSITIVE LOGITS
     altrett
    0.11
    —including
    0.11
    大大å°ıå°ıçļĦ
    0.11
     подÑĢÑıд
    0.11
     걸ì³IJ
    0.10
    ä¹ĭå¤ļ
    0.10
    éĥ½æĺ¯åĽłä¸º
    0.09
    åIJĦå¼ıåIJĦæł·çļĦ
    0.09
     imaginable
    0.09
    缴æİ¥æĪĸéĹ´æİ¥
    0.09
    Activations Density 0.919%

    No Known Activations