© 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. 65228
    Prev
    Next
    INDEX
    Explanations

    disease transmission and infections

    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
    ê¸ī
    -0.07
    éľĸ
    -0.07
     (--
    -0.07
    éŃĤ
    -0.07
    è¡ĢèĤī
    -0.06
    ebes
    -0.06
    å¿łå¿ĥ
    -0.06
    鬼çİĭ
    -0.06
    åĪĩå®ŀåģļåĪ°
    -0.06
     Relief
    -0.06
    POSITIVE LOGITS
     opportun
    0.10
    åĩłçİĩ
    0.09
     susceptibility
    0.09
     infections
    0.09
    æĽ´å®¹æĺĵ
    0.09
    éĺ²èĮĥ
    0.09
    容æĺĵåıijçĶŁ
    0.08
    éĺ²æ²»
    0.08
    é«ĺåıij
    0.08
    æ¦Ĥçİĩ
    0.08
    Activations Density 0.163%

    No Known Activations