© 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. 28594
    Prev
    Next
    INDEX
    Explanations

    increasing momentum

    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
    æ¯Ķäºļ
    -0.09
    æİĸ
    -0.08
     disruption
    -0.08
    obie
    -0.08
    éªĭ
    -0.08
     disruptions
    -0.07
    çĮĿ
    -0.07
    åİŁä»¶åıĬå¤įåį°ä»¶
    -0.07
    åħ¨é¢Ŀ
    -0.07
    ائع
    -0.07
    POSITIVE LOGITS
     gradually
    0.18
     slowly
    0.16
     dần
    0.16
    éĢIJæ¸IJ
    0.15
     progressively
    0.15
     steadily
    0.15
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.15
    ä¼ļéĢIJæ¸IJ
    0.14
    ä¸įæĸŃå¢ŀåĬł
    0.14
     gradual
    0.14
    Activations Density 0.169%

    No Known Activations