© 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. 40084
    Prev
    Next
    INDEX
    Explanations

    Lie groups and algebras

    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
    èĪĮå°ĸ
    -0.07
     utens
    -0.07
    ÙĨج
    -0.07
     figur
    -0.06
     dra
    -0.06
    skal
    -0.06
    æijĨæĶ¾åľ¨
    -0.06
     consign
    -0.06
    æŀķ
    -0.06
    UMMY
    -0.06
    POSITIVE LOGITS
    arella
    0.09
    ynchronously
    0.09
    amma
    0.09
    ssf
    0.08
    éŨæĪ·
    0.08
    æĭīèµ·
    0.08
    SSF
    0.08
    ç»Ħç»ĩä¸Ń
    0.08
    igon
    0.08
     hsv
    0.08
    Activations Density 0.019%

    No Known Activations