© 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. 55780
    Prev
    Next
    INDEX
    Explanations

    array of objects/tuples/dictionaries/strings

    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
    çī¹åĭĴ
    -0.09
    ãĥ¬ãĥ¼ãĥī
    -0.08
    çļĦä¸Ģ家
    -0.08
    ies
    -0.07
    æª
    -0.07
    illac
    -0.07
    illar
    -0.07
    à¥ĩष
    -0.07
    icon
    -0.07
    nowrap
    -0.07
    POSITIVE LOGITS
    alcon
    0.08
     uintptr
    0.07
     integers
    0.07
     tros
    0.07
    ุ
    0.07
    UNET
    0.06
    æķ´æķ°
    0.06
    交æľĭåıĭ
    0.06
    ÙĤØ·
    0.06
    ãģ³
    0.06
    Activations Density 0.039%

    No Known Activations