© 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. 33835
    Prev
    Next
    INDEX
    Explanations

    glass window panels

    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
    淤泥
    -0.08
    åľŁæĸ¹
    -0.08
    æĿ¾è½¯
    -0.07
    Carthy
    -0.07
    ãĥĸãĥ©ãĤ·
    -0.07
    污泥
    -0.07
     Heap
    -0.07
     céré
    -0.07
    çĦĻ
    -0.07
    åľŁçļĦ
    -0.07
    POSITIVE LOGITS
    çİ»çĴĥ
    0.22
     glass
    0.19
     Glass
    0.17
    glass
    0.17
    çļĦçİ»çĴĥ
    0.16
    Glass
    0.16
    éĢıæĺİ
    0.15
    éĢıæĺİçļĦ
    0.15
    ãĤ¬ãĥ©ãĤ¹
    0.15
     ÑģÑĤекла
    0.15
    Activations Density 0.236%

    No Known Activations