© 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. 16624
    Prev
    Next
    INDEX
    Explanations

    increase or decrease quantity

    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
     gar
    -0.08
    为åģļ好
    -0.08
    ç½Ħ
    -0.07
    æīįå¼Ģå§ĭ
    -0.07
    è¨ĺ
    -0.07
    ipas
    -0.07
    æĺłå°Ħ
    -0.07
    絡
    -0.07
    èı²çī¹
    -0.07
    zit
    -0.07
    POSITIVE LOGITS
    å¢ŀ大
    0.13
    å¢ŀåĬł
    0.13
    åĩıå°ı
    0.12
    åĴĮæıIJé«ĺ
    0.11
    increase
    0.11
     increase
    0.11
    æĶ¹åıĺ
    0.10
    Increase
    0.10
    éĻįä½İ
    0.10
     ÑĥвелиÑĩиÑĤÑĮ
    0.10
    Activations Density 0.129%

    No Known Activations