© 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. 10796
    Prev
    Next
    INDEX
    Explanations

    life and lifestyle

    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
    Ñģловно
    -0.08
    ï¸ı
    -0.08
    assin
    -0.08
    ulong
    -0.08
    IMUM
    -0.07
     giang
    -0.07
    à¸ŀัà¸Ļà¸ĺà¹Į
    -0.07
    ãĤĪãģĨãģª
    -0.07
    ê·
    -0.07
     parere
    -0.07
    POSITIVE LOGITS
    çIJIJäºĭ
    0.09
    èµ·å±ħ
    0.08
    å¿ħéľĢåĵģ
    0.08
    Ñīе
    0.08
    ÏĦει
    0.08
    ening
    0.08
    åĴĮå·¥ä½ľ
    0.08
    -threatening
    0.07
    adder
    0.07
    åĨĻçħ§
    0.07
    Activations Density 0.055%

    No Known Activations