© 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. 58180
    Prev
    Next
    INDEX
    Explanations

    what happens

    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¿ĹåĪļ
    -0.09
    æīİåħĭ
    -0.07
    eti
    -0.07
    rava
    -0.07
    ÛĮÙģ
    -0.07
    ThreadId
    -0.07
    มาà¸Īาà¸ģ
    -0.07
    recision
    -0.07
    FetchRequest
    -0.07
    建ç«ĭåľ¨
    -0.07
    POSITIVE LOGITS
    ä¼ļåıijçĶŁ
    0.09
    ä¼ļæľīä»Ģä¹Ī
    0.08
     scenarios
    0.07
     versus
    0.07
    ä¼ļåĩºçİ°
    0.07
     scenario
    0.07
    çļĦåIJİæŀľ
    0.07
    è¿ĻæŶ
    0.07
    ä¼ļ产çĶŁ
    0.07
     då
    0.07
    Activations Density 0.145%

    No Known Activations