© 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. 11842
    Prev
    Next
    INDEX
    Explanations

    photodynamic therapy, radiotherapy, brachytherapy

    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
    ç«ĭ
    -0.07
    ä¹ŀ
    -0.07
    æĵ
    -0.07
    byss
    -0.07
    æĴ
    -0.07
     seasonal
    -0.07
    æĭ¥
    -0.07
     airy
    -0.07
    åŃ£èĬĤæĢ§
    -0.07
    ä¸Ģ缮
    -0.06
    POSITIVE LOGITS
     targeting
    0.13
     targeted
    0.12
    éĿ¶åIJij
    0.12
     localized
    0.09
    target
    0.09
    -target
    0.09
    ç²¾åĩĨ
    0.09
    æĶ¾çĸĹ
    0.08
     radio
    0.08
     targets
    0.08
    Activations Density 0.088%

    No Known Activations