© 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. 17753
    Prev
    Next
    INDEX
    Explanations

    foreign language grammatical structures

    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
     appropriately
    -0.08
    å¯¹æľ¬æ¬¡
    -0.08
    åħ·å¤ĩèī¯å¥½çļĦ
    -0.07
    (None
    -0.07
    ceau
    -0.07
    ventus
    -0.07
    éĢĤéĩıçļĦ
    -0.07
    èĥ½å¤ŁæľīæķĪ
    -0.07
    è·Įåģľ
    -0.07
    ä¼ĺèī¯çļĦ
    -0.07
    POSITIVE LOGITS
     gramm
    0.08
    æĹłè®ºåľ¨
    0.08
     IELTS
    0.07
     situations
    0.07
    æĹłè®º
    0.07
    辨
    0.06
     tricky
    0.06
    æĭIJ弯
    0.06
     determin
    0.06
    secutive
    0.06
    Activations Density 0.019%

    No Known Activations