© 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. 20835
    Prev
    Next
    INDEX
    Explanations

    medical emergency communication

    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
    lices
    -0.07
    çļ®
    -0.07
    arts
    -0.07
    avas
    -0.06
    stadt
    -0.06
    ibi
    -0.06
    ä¹Łå¥½
    -0.06
    lessly
    -0.06
    ì¹ĺìĿĺ
    -0.06
    çĻ½çĻ½
    -0.06
    POSITIVE LOGITS
    ä¸ĵçĶ¨çļĦ
    0.14
    ä¸ĵéŨçļĦ
    0.12
    ä¸ĵçĶ¨
    0.12
    ä¸ĵéŨ
    0.11
    -specific
    0.11
    å°ĪéĸĢ
    0.10
    å°Ī屬
    0.10
    å°ĤçĶ¨ãģ®
    0.09
    ä¸ĵçĶ¨è®¾å¤ĩ
    0.09
     ÑģпеÑĨиалÑĮно
    0.09
    Activations Density 0.250%

    No Known Activations