© 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. 61664
    Prev
    Next
    INDEX
    Explanations

    we/they/us together

    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
    èĩªå·±
    -0.07
     itself
    -0.07
    èĩªèº«
    -0.06
    ï¼Į
    -0.06
    æİĮ
    -0.06
     Grosso
    -0.06
    å¡ŀ
    -0.06
    足
    -0.06
    unk
    -0.06
    ãĢģ
    -0.06
    POSITIVE LOGITS
     berdua
    0.12
    ä¿©
    0.11
    åħ±åIJĮæĪIJéķ¿
    0.11
    åIJĦèĩªçļĦ
    0.11
     juntos
    0.10
    两人çļĦ
    0.10
    åħ±åIJĮè¿ĽæŃ¥
    0.10
    äºĮ人çļĦ
    0.10
    äºĮ人
    0.10
    åħ±åIJĮæݢ讨
    0.09
    Activations Density 0.270%

    No Known Activations