© 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. 10737
    Prev
    Next
    INDEX
    Explanations

    descriptive medical terms

    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
    åĸľæĢĴåĵĢ
    -0.08
    iland
    -0.08
    åĸľæĢĴåĵĢä¹IJ
    -0.08
    зон
    -0.08
    è¿ijå¹³
    -0.07
    reasonable
    -0.07
    æİĸ
    -0.07
    æµ·åŁŁ
    -0.07
    åĴĮ第äºĮ
    -0.07
    Convertible
    -0.07
    POSITIVE LOGITS
    çĬ¶
    0.09
     hallmark
    0.09
    çĬ¶çļĦ
    0.08
     characteristic
    0.08
    -like
    0.07
    çī¹å¾ģ
    0.07
     ÑħаÑĢакÑĤеÑĢ
    0.07
     appearance
    0.07
    è¿Ļæĺ¯ä¸Ģç§į
    0.07
     feature
    0.07
    Activations Density 0.024%

    No Known Activations