© 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. 48576
    Prev
    Next
    INDEX
    Explanations

    other people, competition, fellow

    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
    亲人
    -0.07
    ÑĤин
    -0.07
    AuthToken
    -0.06
    åľ°ä¹ħ
    -0.06
    uum
    -0.06
    ä¸įåĽŀ
    -0.06
    abbr
    -0.06
    -li
    -0.06
    cab
    -0.06
    ecure
    -0.06
    POSITIVE LOGITS
    åIJĮ类产åĵģ
    0.13
    åIJĮç±»
    0.12
    åIJĮä¸ļ
    0.12
     competitor
    0.12
    (other
    0.11
    æ¯ĶæĪij
    0.11
     fellow
    0.11
    åħ¶ä»ĸ人
    0.11
    åIJĮè¡Įä¸ļ
    0.11
    åIJĮè¡Į
    0.11
    Activations Density 0.346%

    No Known Activations