© 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. 23222
    Prev
    Next
    INDEX
    Explanations

    sustainable development

    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
     dã
    -0.08
    lesia
    -0.08
    éİ®
    -0.08
    Ỽn
    -0.08
    ito
    -0.08
    alon
    -0.07
    اضÙĬ
    -0.07
    ики
    -0.07
    oup
    -0.07
     khôi
    -0.07
    POSITIVE LOGITS
    ä¸įäºĨå¤ļä¹ħ
    0.09
    ä¹ħçļĦ
    0.09
    涯
    0.09
    åı¯æĮģç»ŃæĢ§
    0.08
    åı¯æĮģç»Ń
    0.08
    ä¸įæĭĶ
    0.08
    авли
    0.07
     Ø·ÙĪÙĬÙĦ
    0.07
    èques
    0.07
    ood
    0.07
    Activations Density 0.010%

    No Known Activations