© 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. 10593
    Prev
    Next
    INDEX
    Explanations

    book publication details

    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
     COMPUTER
    -0.09
    大è¯Ŀ
    -0.08
     Computer
    -0.08
    æľ¬æĸĩæĿ¥èĩª
    -0.08
    å¸IJ
    -0.08
     dereg
    -0.08
     Technologies
    -0.08
     Trinh
    -0.08
    opers
    -0.08
     transporter
    -0.08
    POSITIVE LOGITS
     Telegram
    0.07
    IOC
    0.06
     Wikimedia
    0.06
    Assertion
    0.06
     definite
    0.06
    indle
    0.06
     aerop
    0.06
    telegram
    0.06
    CIO
    0.06
    ahas
    0.06
    Activations Density 0.369%

    No Known Activations