© 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. 28711
    Prev
    Next
    INDEX
    Explanations

    ejction fraction, reference standard, histologically

    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
    åĸľæ¬¢ä¸Ĭ
    -0.07
     saja
    -0.07
    odzi
    -0.07
    表çİ°åľ¨
    -0.07
     Stol
    -0.06
    ensem
    -0.06
     kandid
    -0.06
    ecker
    -0.06
    áĥIJáĥ®
    -0.06
    让æ¶Īè´¹èĢħ
    -0.06
    POSITIVE LOGITS
    verified
    0.08
     verified
    0.08
    andest
    0.08
    éªĮè¯ģ
    0.08
    对çħ§
    0.08
    Benchmark
    0.08
     benchmark
    0.08
     arro
    0.08
    ä¸įå·®
    0.08
     benchmarks
    0.08
    Activations Density 0.252%

    No Known Activations