© 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. 23209
    Prev
    Next
    INDEX
    Explanations

    independent

    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
    人人
    -0.07
    大ä¸Ń
    -0.07
    æĢ»ä¼ļ
    -0.07
    åĬ¨åĬ¨
    -0.07
    两岸
    -0.06
    ux
    -0.06
    大æłij
    -0.06
    lada
    -0.06
    avr
    -0.06
    spor
    -0.06
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.20
    çĭ¬ç«ĭçļĦ
    0.19
     independent
    0.17
     independently
    0.16
     Independ
    0.16
    çį¨ç«ĭ
    0.16
    çĭ¬ç«ĭæĢ§
    0.16
     ÑģамоÑģÑĤоÑı
    0.15
     ëıħìŀIJ
    0.15
     independ
    0.15
    Activations Density 0.342%

    No Known Activations