© 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. 27122
    Prev
    Next
    INDEX
    Explanations

    group of people

    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
    çļĦå¨ģåĬĽ
    -0.08
    ussy
    -0.07
    ×Ļר×ķת
    -0.07
     involving
    -0.07
    è¿Ļ家ä¼Ļ
    -0.07
     teammate
    -0.06
    äºĮä½į
    -0.06
    å¨ģåĬĽ
    -0.06
    onsense
    -0.06
    ÑīикÑĥ
    -0.06
    POSITIVE LOGITS
     whom
    0.13
    群ä½ĵçļĦ
    0.12
    群ä½ĵ
    0.12
     who
    0.12
    æĺ¯ä¸Ģ群
    0.11
    ä»ĸ们æĺ¯
    0.11
     whose
    0.10
     groups
    0.10
    who
    0.10
     cohorts
    0.10
    Activations Density 0.384%

    No Known Activations