© 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. 64083
    Prev
    Next
    INDEX
    Explanations

    support or alliance

    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
    -0.07
    éĩįç½®
    -0.07
    æĤł
    -0.06
    Pres
    -0.06
    ä¸Ģ次
    -0.06
    éĢĢ
    -0.05
    交äºĴå¼ı
    -0.05
    å¼ķçĶ¨çļĦ
    -0.05
    EQ
    -0.05
    æĭĽå¾ħ
    -0.05
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.14
    éĺµèIJ¥
    0.12
    /support
    0.12
    缣åıĭ
    0.12
    æĶ¯æĮģ
    0.12
    against
    0.12
     allies
    0.12
    çļĦæĶ¯æĮģ
    0.12
     alliance
    0.11
    ç«ĭåľº
    0.11
    Activations Density 0.284%

    No Known Activations