© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59985
    Prev
    Next
    INDEX
    Explanations

    technical and common entities

    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
    Negative Logits
    ä¸Ģéĩij
    -0.06
    ä½Ĩæĺ¯çĶ±äºİ
    -0.06
     tradicional
    -0.06
    éļĶçĿĢ
    -0.06
    æĺĨå±±
    -0.06
    mond
    -0.06
    æīij
    -0.06
     szenved
    -0.06
    ada
    -0.06
     Marr
    -0.06
    POSITIVE LOGITS
    ĵ
    0.08
    ibro
    0.07
    cpy
    0.07
    alainen
    0.07
    uby
    0.07
    mage
    0.07
    lina
    0.07
    hurst
    0.07
    arat
    0.07
    è½»
    0.07
    Activations Density 0.463%

    No Known Activations