© 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. 29210
    Prev
    Next
    INDEX
    Explanations

    gases and mixtures

    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¤ģ
    -0.07
    æĬ¢çľ¼
    -0.07
    orm
    -0.07
    æĬĹæ´ª
    -0.07
    淤泥
    -0.06
    èĤ¾èĻļ
    -0.06
    æįŀåĩº
    -0.06
    æ°´åİĤ
    -0.06
    èĤ¾çĹħ
    -0.06
    æ³¥æ³ŀ
    -0.06
    POSITIVE LOGITS
     gases
    0.18
    æ°Ķä½ĵ
    0.16
     gas
    0.16
    çļĦæ°Ķä½ĵ
    0.15
     air
    0.15
    æ°Ķæµģ
    0.14
    æ°Ķä½ĵçļĦ
    0.14
     воздÑĥÑħа
    0.14
     воздÑĥÑħ
    0.14
    gas
    0.14
    Activations Density 0.222%

    No Known Activations