© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47494
    Prev
    Next
    INDEX
    Explanations

    rates per unit

    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
    ellone
    -0.08
    -lite
    -0.07
    oin
    -0.07
    eningen
    -0.07
    IAL
    -0.07
    欧
    -0.07
    aggio
    -0.06
    ìłģìĿ´
    -0.06
     Mainten
    -0.06
    使çĶ¨è¯¥
    -0.06
    POSITIVE LOGITS
     annually
    0.10
    æ¯ı天
    0.09
     per
    0.09
    æ¯ıå¹´çļĦ
    0.09
    æ¯ıå¹´
    0.09
    æ¯ı天çļĦ
    0.09
    æ¯ıç§Ĵ
    0.08
     daily
    0.08
    æ¯ı天æľī
    0.08
    æ¯ıå°ıæŶ
    0.08
    Activations Density 0.108%

    No Known Activations