© 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. 12050
    Prev
    Next
    INDEX
    Explanations

    bleach/chlorine sanitizers, activated air/water

    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
    èĥļ
    -0.08
    饥
    -0.07
    ovnÃŃ
    -0.07
    æķ´å½¢å¤ĸç§ij
    -0.07
    {"
    -0.06
    纺
    -0.06
     Earl
    -0.06
     Lá»Ļc
    -0.06
    <!--
    -0.06
    har
    -0.06
    POSITIVE LOGITS
    æĿĢèıĮ
    0.10
     bleach
    0.10
    æ¼ĤçĻ½
    0.09
     desinf
    0.08
     chlorine
    0.08
    æ¶ĪæĿĢ
    0.08
    æĿĢæ¯Ĵ
    0.08
    æ¶Īæ¯ĴåīĤ
    0.08
    æ¶Īæ¯Ĵ
    0.08
     Municipal
    0.08
    Activations Density 0.012%

    No Known Activations