© 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. 22739
    Prev
    Next
    INDEX
    Explanations

    simulated or fictional network activity

    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
    å°±æĢķ
    -0.09
    ä¿®çļĦ
    -0.08
    uzu
    -0.08
    untain
    -0.08
    .edit
    -0.07
    ât
    -0.07
    tright
    -0.07
    å®ĮåĸĦäºĨ
    -0.07
    (edit
    -0.07
    ä¿®
    -0.07
    POSITIVE LOGITS
    模æĭŁ
    0.11
     simulated
    0.11
    èĻļæŀĦ
    0.11
     fictional
    0.10
     simulation
    0.10
     simulate
    0.10
    èĻļå¹»
    0.09
     hypothetical
    0.09
    æĥ³è±¡ä¸ŃçļĦ
    0.09
     simulator
    0.08
    Activations Density 0.103%

    No Known Activations