© 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. 16799
    Prev
    Next
    INDEX
    Explanations

    list of dictionaries

    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
    èĶ¬æŀľ
    -0.07
    otar
    -0.07
    夷
    -0.07
    èĭ¥éĿŀ
    -0.07
    åıĬ以ä¸Ĭ
    -0.07
    empio
    -0.07
    çĿ¡çĿĢäºĨ
    -0.06
    erman
    -0.06
    åı¥è¯Ŀ说
    -0.06
     gebra
    -0.06
    POSITIVE LOGITS
    edel
    0.08
    ushima
    0.07
    зима
    0.07
    bey
    0.07
     Dere
    0.07
    reiz
    0.07
    جرÙĬ
    0.07
    elon
    0.07
    ,{"
    0.07
     Presidency
    0.06
    Activations Density 0.001%

    No Known Activations