© 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. 15761
    Prev
    Next
    INDEX
    Explanations

    silica and glass

    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
    æī§çºª
    -0.07
    èĤĽéŨ
    -0.07
     magnet
    -0.07
    çĿ¦
    -0.07
    iability
    -0.07
    luft
    -0.07
    æ²¹åĵģ
    -0.06
    油箱
    -0.06
     kad
    -0.06
    å²±
    -0.06
    POSITIVE LOGITS
     glass
    0.10
    çİ»çĴĥ
    0.09
     glasses
    0.09
    çļĦçİ»çĴĥ
    0.09
     silica
    0.09
    ãĤ¬ãĥ©ãĤ¹
    0.08
     Glasses
    0.08
    ortable
    0.08
    glas
    0.08
    éħ¸éĴł
    0.08
    Activations Density 0.079%

    No Known Activations