© 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. 64027
    Prev
    Next
    INDEX
    Explanations

    demonstrates success or positive outcome

    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
    æķħæĦıçļĦ
    -0.08
    locator
    -0.08
    ä¸Ĭè¿Ľå¿ĥ
    -0.08
    天水
    -0.08
     campa
    -0.08
    åħ¨éĥ¨è¯Ħ论
    -0.07
    γÏĮ
    -0.07
    ç«ĭå¿Ĺ
    -0.07
     Guil
    -0.07
    å·§
    -0.07
    POSITIVE LOGITS
    çļĦç»ıéªĮ
    0.11
    æķĪæŀľ
    0.11
    ç»ıéªĮ
    0.11
    åıįé¦Ī
    0.10
    çļĦæķĪæŀľ
    0.10
     experience
    0.10
    æĪIJåĬŁç»ıéªĮ
    0.10
     feedback
    0.10
     اÙĦتجربة
    0.09
    æķĪæŀľåĴĮ
    0.09
    Activations Density 0.322%

    No Known Activations