© 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. 15943
    Prev
    Next
    INDEX
    Explanations

    pairs, two, two

    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
    çĮ¬
    -0.07
    åIJİèĢħ
    -0.07
    dot
    -0.07
    cul
    -0.06
    对äºİè¿ĻäºĽ
    -0.06
     Builder
    -0.06
     mora
    -0.06
    å±ĪæĮĩ
    -0.06
    ney
    -0.06
     dot
    -0.06
    POSITIVE LOGITS
    çļĦ两个
    0.21
    æĺ¯ä¸¤ä¸ª
    0.20
     pair
    0.20
    çļĦ两
    0.19
    çļĦåıĮ
    0.19
     pairs
    0.18
    two
    0.18
     two
    0.18
    åıĮ
    0.18
    çļĦä¸Ģ对
    0.18
    Activations Density 0.916%

    No Known Activations